me/env-ansible
1
1 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'dev2' into dev

Browse Source 
Pushed on a system when another system still needed to push.
This commit is contained in:
me committed 2026-10-21 09:58:43 -07:00
2 parents 99a0b7ca0b e81de0c63b
commit 0363aefc1d
6 files changed
+297 -97
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

facts/general/package.yml
+1
View File
@@ -22,6 +22,7 @@
alsa: alsa-utils alsa: alsa-utils
stress: stress stress: stress
jq: jq jq: jq
btop: btop
- name: General | Facts | Package | Parrot OS Fixes - name: General | Facts | Package | Parrot OS Fixes
ansible.builtin.set_fact: ansible.builtin.set_fact:
files/settings/i3.config
+7 -5
View File
@@ -300,21 +300,22 @@ assign [class="(?i).*mpv.*"] $ws9
assign [class="(?i).*vpn.*"] $ws0 assign [class="(?i).*vpn.*"] $ws0
assign [class="(?i).*mullvad.*"] $ws0 assign [class="(?i).*mullvad.*"] $ws0
assign [class="(?i).*gnome-system-monitor.*"] $ws0
## Workspace Specific Workflows ## ## Workspace Specific Workflows ##
bindsym $ctrl+$shift+1 workspace $ws1; exec "i3-sensible-terminal & gnome-system-monitor" #bindsym $ctrl+$shift+1 workspace $ws1; exec "i3-sensible-terminal & gnome-system-monitor"
bindsym $ctrl+$shift+1 workspace $ws1; exec "i3-sensible-terminal & i3-sensible-terminal btop -u 500"
bindsym $ctrl+$shift+2 workspace $ws2; exec $FIREFOX bindsym $ctrl+$shift+2 workspace $ws2; exec $FIREFOX
bindsym $ctrl+$shift+3 workspace $ws3; exec "(codium || vscodium || codium-flatpak || vscodium-flatpak)" bindsym $ctrl+$shift+3 workspace $ws3; exec "(codium || vscodium || codium-flatpak || vscodium-flatpak)"
bindsym $ctrl+$shift+4 workspace $ws4; exec "android-studio || android-studio-flatpak" bindsym $ctrl+$shift+4 workspace $ws4; exec "android-studio || android-studio-flatpak"
bindsym $ctrl+$shift+5 workspace $ws5; exec "(signal || signal-flatpak) & (dino || dino-flatpak)" bindsym $ctrl+$shift+5 workspace $ws5; exec "(signal || signal-flatpak) & (dino || dino-flatpak)"
# & (forkgram || forkgram-flatpak || telegram || telegram-flatpak)" bindsym $alt+$shift+5 workspace $ws5; exec "(session || session-flatpak) & (forkgram || forkgram-flatpak || telegram || telegram-flatpak)"
bindsym $alt+$shift+5 workspace $ws5; exec "(forkgram || forkgram-flatpak || telegram || telegram-flatpak) & (session || session-flatpak)"
bindsym $ctrl+$shift+6 workspace $ws6; exec "pavucontrol & blueman-manager" bindsym $ctrl+$shift+6 workspace $ws6; exec "pavucontrol & blueman-manager"
bindsym $ctrl+$shift+7 workspace $ws7; exec $TRANSMISSION bindsym $ctrl+$shift+7 workspace $ws7; exec $TRANSMISSION
bindsym $ctrl+$shift+8 workspace $ws8; exec strawberry bindsym $ctrl+$shift+8 workspace $ws8; exec strawberry
bindsym $ctrl+$shift+9 workspace $ws9; exec thunar bindsym $ctrl+$shift+9 workspace $ws9; exec thunar
bindsym $ctrl+$shift+0 workspace $ws0; exec mullvad-vpn bindsym $ctrl+$shift+0 workspace $ws0; exec "mullvad-vpn & gnome-system-monitor"
## Reloads, Restarts, Exit ## ## Reloads, Restarts, Exit ##
@@ -395,11 +396,12 @@ bar {
# Workspace 1 # Workspace 1
exec --no-startup-id i3-sensible-terminal exec --no-startup-id i3-sensible-terminal
exec --no-startup-id gnome-system-monitor exec --no-startup-id i3-sensible-terminal btop -u 500
# Respective Workspaces # Respective Workspaces
exec --no-startup-id mullvad-vpn exec --no-startup-id mullvad-vpn
exec --no-startup-id $TRANSMISSION exec --no-startup-id $TRANSMISSION
exec --no-startup-id gnome-system-monitor
# Set defaults for laptop backlights. # Set defaults for laptop backlights.
exec --no-startup-id "light -S 20; light -N 5; light -O" exec --no-startup-id "light -S 20; light -N 5; light -O"
files/settings/open_webui_roleplays.json
+93 -29
View File
@@ -1,10 +1,10 @@
[ [
{ {
"version_id": "a0084dd8-2834-4222-8a25-b8986d535ee4", "version_id": "b292c75d-b2d8-45d9-9f89-f57f2acd250b",
"id": "coder-junior", "id": "coder-junior",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704", "user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "qwen3.6:27b", "base_model_id": "qwen3.6:27b",
"name": "Coder (Junior) [256k,20GB]", "name": "Code-Jr [256k,20GB]",
"params": { "params": {
"custom_params": {}, "custom_params": {},
"num_ctx": 256000, "num_ctx": 256000,
@@ -64,16 +64,16 @@
}, },
"access_grants": [], "access_grants": [],
"is_active": true, "is_active": true,
"updated_at": 1792575797, "updated_at": 1792596704,
"created_at": 1792539937, "created_at": 1792539937,
"background_image_data": null "background_image_data": null
}, },
{ {
"version_id": "0e733446-911d-4d52-805f-7a9d6d863636", "version_id": "ac4dd0f5-9cf0-450f-b188-c275e2a5e74b",
"id": "coder-senior", "id": "coder-senior",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704", "user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "qwen3.8:27b", "base_model_id": "qwen3.8:27b",
"name": "Coder (Senior) [256k,20GB]", "name": "Code-Sr [256k,20GB]",
"params": { "params": {
"custom_params": {}, "custom_params": {},
"num_ctx": 256000, "num_ctx": 256000,
@@ -133,16 +133,16 @@
}, },
"access_grants": [], "access_grants": [],
"is_active": true, "is_active": true,
"updated_at": 1792575797, "updated_at": 1792596711,
"created_at": 1792539958, "created_at": 1792539958,
"background_image_data": null "background_image_data": null
}, },
{ {
"version_id": "4f412e1f-ec8e-4724-997f-7dd7a5b75c39", "version_id": "97101e67-3332-457e-95a9-73c89ee9d87a",
"id": "coder-entry", "id": "coder-entry",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704", "user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "codestral:22b", "base_model_id": "codestral:22b",
"name": "Coder (Entry) [256k,20GB]", "name": "Code-Entry [256k,20GB]",
"params": { "params": {
"custom_params": {}, "custom_params": {},
"num_ctx": 256000, "num_ctx": 256000,
@@ -202,16 +202,16 @@
}, },
"access_grants": [], "access_grants": [],
"is_active": true, "is_active": true,
"updated_at": 1792575797, "updated_at": 1792596722,
"created_at": 1792542461, "created_at": 1792542461,
"background_image_data": null "background_image_data": null
}, },
{ {
"version_id": "351021ce-1a76-461d-82c9-63c5b5537649", "version_id": "a08b4144-4fda-4bb0-8376-e42a76ca373f",
"id": "language-micro", "id": "language-micro",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704", "user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "ministral-3:8b", "base_model_id": "ministral-3:8b",
"name": "Language (Micro) [32k,10GB]", "name": "Lang-Mini8 [32k,10GB]",
"params": { "params": {
"system": "Please use the attached Knowledge Base files as your personality.", "system": "Please use the attached Knowledge Base files as your personality.",
"custom_params": {}, "custom_params": {},
@@ -266,16 +266,16 @@
}, },
"access_grants": [], "access_grants": [],
"is_active": true, "is_active": true,
"updated_at": 1792575797, "updated_at": 1792596791,
"created_at": 1792542993, "created_at": 1792542993,
"background_image_data": null "background_image_data": null
}, },
{ {
"version_id": "5fbfe995-80be-46bf-a369-6f5817fa08be", "version_id": "9f920e0c-1af2-4360-9714-1d1ac431c927",
"id": "language-tiny", "id": "language-tiny",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704", "user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "ministral-3:3b", "base_model_id": "ministral-3:3b",
"name": "Language (Tiny) [32k,5.9GB]", "name": "Lang-Mini3 [32k,5.9GB]",
"params": { "params": {
"system": "Please use the attached Knowledge Base files as your personality.", "system": "Please use the attached Knowledge Base files as your personality.",
"custom_params": {}, "custom_params": {},
@@ -330,16 +330,16 @@
}, },
"access_grants": [], "access_grants": [],
"is_active": true, "is_active": true,
"updated_at": 1792575797, "updated_at": 1792596783,
"created_at": 1792543028, "created_at": 1792543028,
"background_image_data": null "background_image_data": null
}, },
{ {
"version_id": "8f97ecbd-641a-4f44-aa0d-a177fb1140a4", "version_id": "79e6f9b5-18d7-4d35-bf51-794016627bf4",
"id": "language-small", "id": "language-small",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704", "user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "mistral-small3.2:24b", "base_model_id": "mistral-small3.2:24b",
"name": "Language (Small) [64k,26GB]", "name": "Lang-Small24 [64k,26GB]",
"params": { "params": {
"system": "Please use the attached Knowledge Base files as your personality.", "system": "Please use the attached Knowledge Base files as your personality.",
"custom_params": {}, "custom_params": {},
@@ -394,16 +394,16 @@
}, },
"access_grants": [], "access_grants": [],
"is_active": true, "is_active": true,
"updated_at": 1792575797, "updated_at": 1792596852,
"created_at": 1792573569, "created_at": 1792573569,
"background_image_data": null "background_image_data": null
}, },
{ {
"version_id": "d6a63f73-41db-463c-8733-7f00b8519bf2", "version_id": "d5657244-5bd0-4858-bda5-24dd6c45128b",
"id": "coder-quick", "id": "coder-moe",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704", "user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "qwen3.6:35b", "base_model_id": "qwen3.6:35b",
"name": "Coder (Quick) [256k,23GB]", "name": "Code-MoE [256k,23GB]",
"params": { "params": {
"custom_params": {}, "custom_params": {},
"num_ctx": 256000, "num_ctx": 256000,
@@ -463,16 +463,16 @@
}, },
"access_grants": [], "access_grants": [],
"is_active": true, "is_active": true,
"updated_at": 1792580114, "updated_at": 1792596766,
"created_at": 1792573569, "created_at": 1792596052,
"background_image_data": null "background_image_data": null
}, },
{ {
"version_id": "c3b51522-a3cc-4567-a22a-fa4d3f31197f", "version_id": "8fef2e35-68b2-4b68-a90f-69f66cd07782",
"id": "coder-architect", "id": "coder-architect",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704", "user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "devstral-small-2:24b", "base_model_id": "devstral-small-2:24b",
"name": "Coder (Architect) [192k,47GB]", "name": "Code-Arch [192k,47GB]",
"params": { "params": {
"custom_params": {}, "custom_params": {},
"num_ctx": 192000, "num_ctx": 192000,
@@ -532,16 +532,16 @@
}, },
"access_grants": [], "access_grants": [],
"is_active": true, "is_active": true,
"updated_at": 1792575797, "updated_at": 1792596744,
"created_at": 1792573569, "created_at": 1792573569,
"background_image_data": null "background_image_data": null
}, },
{ {
"version_id": "3ed809e0-f183-46c7-bf55-34ef18179f80", "version_id": "e7f4e16a-2fc4-41f9-b7c4-097bdcf63db6",
"id": "language-mini", "id": "language-mini",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704", "user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "ministral-3:14b", "base_model_id": "ministral-3:14b",
"name": "Language (Mini) [32k,13GB]", "name": "Lang-Mini14 [32k,13GB]",
"params": { "params": {
"system": "Please use the attached Knowledge Base files as your personality.", "system": "Please use the attached Knowledge Base files as your personality.",
"custom_params": {}, "custom_params": {},
@@ -596,8 +596,72 @@
}, },
"access_grants": [], "access_grants": [],
"is_active": true, "is_active": true,
"updated_at": 1792575797, "updated_at": 1792596774,
"created_at": 1792573569, "created_at": 1792573569,
"background_image_data": null "background_image_data": null
},
{
"version_id": "94031db1-bb29-4c2e-b8ca-540750c33ce9",
"id": "language-moe",
"user_id": "2e2e7554-11f1-4047-8ca4-b04070ccc704",
"base_model_id": "qwen3.5:35b",
"name": "Lang-MoE [256k,28GB]",
"params": {
"system": "Please use the attached Knowledge Base files as your personality.",
"custom_params": {},
"num_thread": 7,
"num_ctx": 64000
},
"meta": {
"profile_image_url": "/static/favicon.png",
"background_image_url": null,
"description": null,
"i18n": null,
"capabilities": {
"file_context": true,
"vision": true,
"file_upload": true,
"web_search": true,
"image_generation": true,
"code_interpreter": true,
"terminal": true,
"citations": true,
"status_updates": true,
"usage": true,
"memory": true,
"builtin_tools": true
},
"knowledge": [
{
"id": "120fa5c0-7f02-4cf3-a136-07b92b042d48",
"name": "Base.md",
"type": "file"
},
{
"id": "bb929f41-18c0-4177-8139-fabfde2b8235",
"name": "Language.md",
"type": "file"
}
],
"voice": null,
"voice_avatar": null,
"suggestion_prompts": null,
"tags": [
{
"name": "language"
}
],
"terminalId": "0f44afba-4f8e-4699-abfd-7c49b61457fe",
"defaultFeatureIds": [
"web_search",
"image_generation",
"code_interpreter"
]
},
"access_grants": [],
"is_active": true,
"updated_at": 1792596751,
"created_at": 1792595834,
"background_image_data": null
} }
] ]
tasks/general/software/packages.yml
+1
View File
@@ -68,6 +68,7 @@
- "{{ alsa }}" - "{{ alsa }}"
- "{{ stress }}" - "{{ stress }}"
- "{{ jq }}" - "{{ jq }}"
- "{{ btop }}"
state: present state: present
- name: General | Software | Packages | Install Software (DEV) - name: General | Software | Packages | Install Software (DEV)
tasks/workstation/linux/software/llm.md
+149 -53
View File
@@ -103,11 +103,28 @@ TBD
#### ministral-3:14b #### ministral-3:14b
```console
$ for m in ministral-3:14b ministral-3:3b codestral:22b qwen2.5-coder:32b qwen3.5:35b qwen3.5:27b; do for c in 128000; do ollama_threads $m $c; done; done
Stopping all ollama usage...
Wed Oct 21 07:24:36 AM MST 2026 - ministral-3:14b w/ 0 Thread(s): tokens/sec: 4.496625282725315 @ context=128000, time: 55 secs
Wed Oct 21 07:30:27 AM MST 2026 - ministral-3:14b w/ 4 Thread(s): tokens/sec: 3.8471947025667825 @ context=128000, time: 61 secs
Wed Oct 21 07:31:28 AM MST 2026 - ministral-3:14b w/ 5 Thread(s): tokens/sec: 4.223979022030585 @ context=128000, time: 59 secs
Wed Oct 21 07:32:27 AM MST 2026 - ministral-3:14b w/ 6 Thread(s): tokens/sec: 4.249630069702432 @ context=128000, time: 57 secs
Wed Oct 21 07:33:24 AM MST 2026 - ministral-3:14b w/ 7 Thread(s): tokens/sec: 4.123533524209736 @ context=128000, time: 54 secs
```
#### ministral-3:8b
TBD TBD
#### ministral-3:3b #### ministral-3:3b
TBD ```console
Wed Oct 21 07:49:37 AM MST 2026 - ministral-3:3b w/ 4 Thread(s): tokens/sec: 14.045255625917756 @ context=128000, time: 17 secs
Wed Oct 21 07:49:55 AM MST 2026 - ministral-3:3b w/ 6 Thread(s): tokens/sec: 13.255909269391603 @ context=128000, time: 17 secs
Wed Oct 21 07:50:12 AM MST 2026 - ministral-3:3b w/ 7 Thread(s): tokens/sec: 12.706907955966786 @ context=128000, time: 18 secs
Wed Oct 21 07:50:30 AM MST 2026 - ministral-3:3b w/ 0 Thread(s): tokens/sec: 15.354264377193688 @ context=128000, time: 17 secs
```
### Larger Models ### Larger Models
@@ -116,83 +133,162 @@ TBD
```console ```console
$ ollama-cpu qwen3.8:27b $ ollama-cpu qwen3.8:27b
Stopping all ollama usage... Stopping all ollama usage...
Wed Oct 21 04:42:04 AM MST 2026 - Model qwen3.8:27b w/ 1 Thread(s), tokens/sec: 0.7746121685803296 @ context=257000 Wed Oct 21 04:44:54 AM MST 2026 - qwen3.8:27b w/ 4 Thread(s), tokens/sec: 2.024676406965962 @ context=257000
Wed Oct 21 04:43:28 AM MST 2026 - Model qwen3.8:27b w/ 2 Thread(s), tokens/sec: 1.6705309718150672 @ context=257000 Wed Oct 21 04:45:39 AM MST 2026 - qwen3.8:27b w/ 5 Thread(s), tokens/sec: 2.0480156821567044 @ context=257000
Wed Oct 21 04:44:12 AM MST 2026 - Model qwen3.8:27b w/ 3 Thread(s), tokens/sec: 2.104312894492908 @ context=257000 Wed Oct 21 04:46:19 AM MST 2026 - qwen3.8:27b w/ 6 Thread(s), tokens/sec: 2.184879704982382 @ context=257000
Wed Oct 21 04:44:54 AM MST 2026 - Model qwen3.8:27b w/ 4 Thread(s), tokens/sec: 2.024676406965962 @ context=257000 Wed Oct 21 04:46:58 AM MST 2026 - qwen3.8:27b w/ 7 Thread(s), tokens/sec: 2.4228105619148526 @ context=257000
Wed Oct 21 04:45:39 AM MST 2026 - Model qwen3.8:27b w/ 5 Thread(s), tokens/sec: 2.0480156821567044 @ context=257000 Wed Oct 21 04:47:36 AM MST 2026 - qwen3.8:27b w/ 8 Thread(s), tokens/sec: 2.472564250465107 @ context=257000
Wed Oct 21 04:46:19 AM MST 2026 - Model qwen3.8:27b w/ 6 Thread(s), tokens/sec: 2.184879704982382 @ context=257000
Wed Oct 21 04:46:58 AM MST 2026 - Model qwen3.8:27b w/ 7 Thread(s), tokens/sec: 2.4228105619148526 @ context=257000
Wed Oct 21 04:47:36 AM MST 2026 - Model qwen3.8:27b w/ 8 Thread(s), tokens/sec: 2.472564250465107 @ context=257000
Wed Oct 21 04:48:23 AM MST 2026 - Model qwen3.8:27b w/ 9 Thread(s), tokens/sec: 2.399352715711734 @ context=257000
Wed Oct 21 04:49:02 AM MST 2026 - Model qwen3.8:27b w/ 10 Thread(s), tokens/sec: 2.7001138401057605 @ context=257000
Wed Oct 21 04:49:36 AM MST 2026 - Model qwen3.8:27b w/ 11 Thread(s), tokens/sec: 2.216459555312583 @ context=257000
Wed Oct 21 04:50:27 AM MST 2026 - Model qwen3.8:27b w/ 12 Thread(s), tokens/sec: 2.228007424406279 @ context=257000
``` ```
```console ```console
$ ollama-cpu qwen3.8:27b 32000 $ ollama-cpu qwen3.8:27b 32000
Stopping all ollama usage... Stopping all ollama usage...
Wed Oct 21 04:54:29 AM MST 2026 - Model qwen3.8:27b w/ 1 Thread(s), tokens/sec: 1.1388177022378907 @ context=32000 Wed Oct 21 04:56:51 AM MST 2026 - qwen3.8:27b w/ 4 Thread(s), tokens/sec: 1.9083129860906882 @ context=32000
Wed Oct 21 04:55:29 AM MST 2026 - Model qwen3.8:27b w/ 2 Thread(s), tokens/sec: 1.388676019472746 @ context=32000 Wed Oct 21 04:57:30 AM MST 2026 - qwen3.8:27b w/ 5 Thread(s), tokens/sec: 2.727908205888872 @ context=32000
Wed Oct 21 04:56:22 AM MST 2026 - Model qwen3.8:27b w/ 3 Thread(s), tokens/sec: 2.3505103465458905 @ context=32000 Wed Oct 21 04:58:00 AM MST 2026 - qwen3.8:27b w/ 6 Thread(s), tokens/sec: 2.133796334310243 @ context=32000
Wed Oct 21 04:56:51 AM MST 2026 - Model qwen3.8:27b w/ 4 Thread(s), tokens/sec: 1.9083129860906882 @ context=32000 Wed Oct 21 04:58:35 AM MST 2026 - qwen3.8:27b w/ 7 Thread(s), tokens/sec: 2.6835810717324833 @ context=32000
Wed Oct 21 04:57:30 AM MST 2026 - Model qwen3.8:27b w/ 5 Thread(s), tokens/sec: 2.727908205888872 @ context=32000 Wed Oct 21 04:59:04 AM MST 2026 - qwen3.8:27b w/ 8 Thread(s), tokens/sec: 2.5231895597861493 @ context=32000
Wed Oct 21 04:58:00 AM MST 2026 - Model qwen3.8:27b w/ 6 Thread(s), tokens/sec: 2.133796334310243 @ context=32000
Wed Oct 21 04:58:35 AM MST 2026 - Model qwen3.8:27b w/ 7 Thread(s), tokens/sec: 2.6835810717324833 @ context=32000
Wed Oct 21 04:59:04 AM MST 2026 - Model qwen3.8:27b w/ 8 Thread(s), tokens/sec: 2.5231895597861493 @ context=32000
Wed Oct 21 04:59:38 AM MST 2026 - Model qwen3.8:27b w/ 9 Thread(s), tokens/sec: 2.512777473452506 @ context=32000
Wed Oct 21 05:00:06 AM MST 2026 - Model qwen3.8:27b w/ 10 Thread(s), tokens/sec: 2.3125143809488065 @ context=32000
Wed Oct 21 05:00:48 AM MST 2026 - Model qwen3.8:27b w/ 11 Thread(s), tokens/sec: 2.700281667801969 @ context=32000
Wed Oct 21 05:01:20 AM MST 2026 - Model qwen3.8:27b w/ 12 Thread(s), tokens/sec: 2.6798394650721127 @ context=32000
``` ```
#### qwen3.6:27b #### qwen3.6:27b
TBD ```console
$ for m in qwen3.6:27b mistral-small3.2:24b ministral-3:14b ministral-3:3b codestral:22b qwen2.5-coder:32b; do for c in 32000 128000 256000; do ollama_threads $m $c; done; done
Stopping all ollama usage...
Wed Oct 21 06:27:01 AM MST 2026 - qwen3.6:27b w/ 4 Thread(s): tokens/sec: 2.7334336715235645 @ context=32000, time: 118 secs
Wed Oct 21 06:28:59 AM MST 2026 - qwen3.6:27b w/ 5 Thread(s): tokens/sec: 2.4123293729892428 @ context=32000, time: 322 secs
Wed Oct 21 06:34:21 AM MST 2026 - qwen3.6:27b w/ 6 Thread(s): tokens/sec: 3.13023193776124 @ context=32000, time: 100 secs
Wed Oct 21 06:36:01 AM MST 2026 - qwen3.6:27b w/ 7 Thread(s): tokens/sec: 2.8468948357981065 @ context=32000, time: 118 secs
Wed Oct 21 06:16:55 AM MST 2026 - qwen3.6:27b w/ 0 Thread(s): tokens/sec: 2.9964513666573485 @ context=32000, time: 122 secs
Stopping all ollama usage...
Wed Oct 21 06:45:42 AM MST 2026 - qwen3.6:27b w/ 4 Thread(s): tokens/sec: 2.978761247100222 @ context=128000, time: 79 secs
Wed Oct 21 06:47:01 AM MST 2026 - qwen3.6:27b w/ 5 Thread(s): tokens/sec: 2.9705167965150583 @ context=128000, time: 79 secs
Wed Oct 21 06:48:20 AM MST 2026 - qwen3.6:27b w/ 6 Thread(s): tokens/sec: 2.778849178516606 @ context=128000, time: 71 secs
Wed Oct 21 06:49:31 AM MST 2026 - qwen3.6:27b w/ 7 Thread(s): tokens/sec: 3.0804550493595095 @ context=128000, time: 76 secs
Wed Oct 21 06:38:00 AM MST 2026 - qwen3.6:27b w/ 0 Thread(s): tokens/sec: 2.7734041760644956 @ context=128000, time: 75 secs
Stopping all ollama usage...
Wed Oct 21 06:57:59 AM MST 2026 - qwen3.6:27b w/ 4 Thread(s): tokens/sec: 2.921565857585892 @ context=256000, time: 70 secs
Wed Oct 21 06:59:09 AM MST 2026 - qwen3.6:27b w/ 5 Thread(s): tokens/sec: 2.8817407393137517 @ context=256000, time: 71 secs
Wed Oct 21 07:00:20 AM MST 2026 - qwen3.6:27b w/ 6 Thread(s): tokens/sec: 2.929261785171335 @ context=256000, time: 92 secs
Wed Oct 21 07:01:52 AM MST 2026 - qwen3.6:27b w/ 7 Thread(s): tokens/sec: 3.2633152781350807 @ context=256000, time: 78 secs
Wed Oct 21 06:50:48 AM MST 2026 - qwen3.6:27b w/ 0 Thread(s): tokens/sec: 2.892592086714092 @ context=256000, time: 76 secs
```
#### qwen3.5:27b
This one is weird. Might need a re-do to confirm?
```console
Wed Oct 21 07:59:14 AM MST 2026 - qwen3.5:27b w/ 4 Thread(s): tokens/sec: 2.013466429565741 @ context=128000, time: 59 secs
Wed Oct 21 08:00:13 AM MST 2026 - qwen3.5:27b w/ 6 Thread(s): tokens/sec: 1.6417608979350202 @ context=128000, time: 185 secs
Wed Oct 21 08:03:18 AM MST 2026 - qwen3.5:27b w/ 7 Thread(s): tokens/sec: 1.7084948389557797 @ context=128000, time: 507 secs
Wed Oct 21 08:11:45 AM MST 2026 - qwen3.5:27b w/ 0 Thread(s): tokens/sec: 2.0470935786636977 @ context=128000, time: 320 secs
```
#### qwen2.5-coder:32b
```console
Wed Oct 21 07:53:00 AM MST 2026 - qwen2.5-coder:32b w/ 4 Thread(s): tokens/sec: 1.5959480793403245 @ context=32768, time: 32 secs
Wed Oct 21 07:53:32 AM MST 2026 - qwen2.5-coder:32b w/ 6 Thread(s): tokens/sec: 1.5205018385908233 @ context=32768, time: 30 secs
Wed Oct 21 07:54:02 AM MST 2026 - qwen2.5-coder:32b w/ 7 Thread(s): tokens/sec: 1.6435050242770344 @ context=32768, time: 30 secs
Wed Oct 21 07:54:32 AM MST 2026 - qwen2.5-coder:32b w/ 0 Thread(s): tokens/sec: 1.616470672291769 @ context=32768, time: 31 secs
```
#### devstral-small-2:24b #### devstral-small-2:24b
```console
$ for c in 32000 128000 192000; do ollama_threads devstral-small-2:24b $c; done
Stopping all ollama usage...
Wed Oct 21 06:05:11 AM MST 2026 - devstral-small-2:24b w/ 4 Thread(s): tokens/sec: 2.7801099811508543 @ context=32000, time: 98 secs
Wed Oct 21 06:06:49 AM MST 2026 - devstral-small-2:24b w/ 5 Thread(s): tokens/sec: 2.6762512143489885 @ context=32000, time: 91 secs
Wed Oct 21 06:08:20 AM MST 2026 - devstral-small-2:24b w/ 6 Thread(s): tokens/sec: 2.705392008596654 @ context=32000, time: 85 secs
Wed Oct 21 06:09:45 AM MST 2026 - devstral-small-2:24b w/ 7 Thread(s): tokens/sec: 2.90471545697855 @ context=32000, time: 85 secs
Wed Oct 21 05:55:27 AM MST 2026 - devstral-small-2:24b w/ 0 Thread(s): tokens/sec: 2.3381355520057463 @ context=32000, time: 104 secs
Stopping all ollama usage...
TBD TBD
```
#### mistral-small-3.2:??b #### mistral-small-3.2:24b
TBD ```console
$ for m in mistral-small3.2:24b ministral-3:14b ministral-3:3b codestral:22b qwen2.5-coder:32b qwen3.5:35b qwen3.5:27b; do for c in 128000; do ollama_threads $m $c; done; done
Stopping all ollama usage...
Wed Oct 21 07:18:16 AM MST 2026 - mistral-small3.2:24b w/ 4 Thread(s): tokens/sec: 2.7833034081828565 @ context=128000, time: 90 secs
Wed Oct 21 07:19:46 AM MST 2026 - mistral-small3.2:24b w/ 5 Thread(s): tokens/sec: 2.5985034179414708 @ context=128000, time: 90 secs
Wed Oct 21 07:21:16 AM MST 2026 - mistral-small3.2:24b w/ 6 Thread(s): tokens/sec: 2.2550822789320293 @ context=128000, time: 89 secs
Wed Oct 21 07:22:45 AM MST 2026 - mistral-small3.2:24b w/ 7 Thread(s): tokens/sec: 2.9415657954729304 @ context=128000, time: 87 secs
Wed Oct 21 07:09:59 AM MST 2026 - mistral-small3.2:24b w/ 0 Thread(s): tokens/sec: 2.9048032082970474 @ context=128000, time: 79 secs
```
#### codestral:22b
```console
Wed Oct 21 07:50:47 AM MST 2026 - codestral:22b w/ 4 Thread(s): tokens/sec: 3.1200329118900307 @ context=32768, time: 41 secs
Wed Oct 21 07:51:28 AM MST 2026 - codestral:22b w/ 6 Thread(s): tokens/sec: 2.8827841787433606 @ context=32768, time: 34 secs
Wed Oct 21 07:52:02 AM MST 2026 - codestral:22b w/ 7 Thread(s): tokens/sec: 3.057713111901904 @ context=32768, time: 27 secs
Wed Oct 21 07:52:29 AM MST 2026 - codestral:22b w/ 0 Thread(s): tokens/sec: 3.0179434414117803 @ context=32768, time: 31 secs
```
### MoE Models ### MoE Models
#### qwen3.6:35b #### qwen3.6:35b
Tests WAY faster than the dense models. Context does not seem to affect timing.
```console ```console
$ for c in 16000 32000 64000 96000 128000 192000 256000; do ollama_threads qwen3.6:35b $c; done $ for c in 16000 32000 64000 96000 128000 192000 256000; do ollama_threads qwen3.6:35b $c; done
Stopping all ollama usage... Stopping all ollama usage...
Wed Oct 21 05:02:48 AM MST 2026 - Model qwen3.6:35b w/ 1 Thread(s), tokens/sec: 6.247414587381804 @ context=16000 Wed Oct 21 05:04:37 AM MST 2026 - qwen3.6:35b w/ 4 Thread(s), tokens/sec: 14.679419453925597 @ context=16000
Wed Oct 21 05:03:37 AM MST 2026 - Model qwen3.6:35b w/ 2 Thread(s), tokens/sec: 10.940551196032734 @ context=16000 Wed Oct 21 05:05:11 AM MST 2026 - qwen3.6:35b w/ 5 Thread(s), tokens/sec: 13.831044087619176 @ context=16000
Wed Oct 21 05:04:09 AM MST 2026 - Model qwen3.6:35b w/ 3 Thread(s), tokens/sec: 13.337110328883416 @ context=16000 Wed Oct 21 05:05:43 AM MST 2026 - qwen3.6:35b w/ 6 Thread(s), tokens/sec: 13.752831594816088 @ context=16000
Wed Oct 21 05:04:37 AM MST 2026 - Model qwen3.6:35b w/ 4 Thread(s), tokens/sec: 14.679419453925597 @ context=16000 Wed Oct 21 05:06:09 AM MST 2026 - qwen3.6:35b w/ 7 Thread(s), tokens/sec: 14.603026210396049 @ context=16000
Wed Oct 21 05:05:11 AM MST 2026 - Model qwen3.6:35b w/ 5 Thread(s), tokens/sec: 13.831044087619176 @ context=16000 Wed Oct 21 05:06:37 AM MST 2026 - qwen3.6:35b w/ 8 Thread(s), tokens/sec: 14.376794631809172 @ context=16000
Wed Oct 21 05:05:43 AM MST 2026 - Model qwen3.6:35b w/ 6 Thread(s), tokens/sec: 13.752831594816088 @ context=16000
Wed Oct 21 05:06:09 AM MST 2026 - Model qwen3.6:35b w/ 7 Thread(s), tokens/sec: 14.603026210396049 @ context=16000
Wed Oct 21 05:06:37 AM MST 2026 - Model qwen3.6:35b w/ 8 Thread(s), tokens/sec: 14.376794631809172 @ context=16000
Wed Oct 21 05:07:05 AM MST 2026 - Model qwen3.6:35b w/ 9 Thread(s), tokens/sec: 8.313997206415827 @ context=16000
Wed Oct 21 05:07:43 AM MST 2026 - Model qwen3.6:35b w/ 10 Thread(s), tokens/sec: 7.6791421803383955 @ context=16000
Wed Oct 21 05:08:20 AM MST 2026 - Model qwen3.6:35b w/ 11 Thread(s), tokens/sec: 7.554472381570082 @ context=16000
Wed Oct 21 05:09:04 AM MST 2026 - Model qwen3.6:35b w/ 12 Thread(s), tokens/sec: 5.6568033831630835 @ context=16000
Stopping all ollama usage... Stopping all ollama usage...
Wed Oct 21 05:09:46 AM MST 2026 - Model qwen3.6:35b w/ 1 Thread(s), tokens/sec: 6.558900659595539 @ context=32000 Wed Oct 21 05:11:39 AM MST 2026 - qwen3.6:35b w/ 4 Thread(s), tokens/sec: 13.683089387469174 @ context=32000
Wed Oct 21 05:10:28 AM MST 2026 - Model qwen3.6:35b w/ 2 Thread(s), tokens/sec: 10.676325434530082 @ context=32000 Wed Oct 21 05:12:04 AM MST 2026 - qwen3.6:35b w/ 5 Thread(s), tokens/sec: 13.447667625607968 @ context=32000
Wed Oct 21 05:11:11 AM MST 2026 - Model qwen3.6:35b w/ 3 Thread(s), tokens/sec: 12.007117299908693 @ context=32000 Wed Oct 21 05:12:31 AM MST 2026 - qwen3.6:35b w/ 6 Thread(s), tokens/sec: 11.170529760956333 @ context=32000
Wed Oct 21 05:11:39 AM MST 2026 - Model qwen3.6:35b w/ 4 Thread(s), tokens/sec: 13.683089387469174 @ context=32000 Wed Oct 21 05:12:57 AM MST 2026 - qwen3.6:35b w/ 7 Thread(s), tokens/sec: 13.448480713710353 @ context=32000
Wed Oct 21 05:12:04 AM MST 2026 - Model qwen3.6:35b w/ 5 Thread(s), tokens/sec: 13.447667625607968 @ context=32000 Wed Oct 21 05:13:27 AM MST 2026 - qwen3.6:35b w/ 8 Thread(s), tokens/sec: 13.143672445847205 @ context=32000
Wed Oct 21 05:12:31 AM MST 2026 - Model qwen3.6:35b w/ 6 Thread(s), tokens/sec: 11.170529760956333 @ context=32000
Wed Oct 21 05:12:57 AM MST 2026 - Model qwen3.6:35b w/ 7 Thread(s), tokens/sec: 13.448480713710353 @ context=32000
Wed Oct 21 05:13:27 AM MST 2026 - Model qwen3.6:35b w/ 8 Thread(s), tokens/sec: 13.143672445847205 @ context=32000
Wed Oct 21 05:13:50 AM MST 2026 - Model qwen3.6:35b w/ 9 Thread(s), tokens/sec: 7.9688801054121505 @ context=32000
Wed Oct 21 05:14:21 AM MST 2026 - Model qwen3.6:35b w/ 10 Thread(s), tokens/sec: 7.064418756844208 @ context=32000
Wed Oct 21 05:14:53 AM MST 2026 - Model qwen3.6:35b w/ 11 Thread(s), tokens/sec: 7.387867650986557 @ context=32000
Wed Oct 21 05:15:30 AM MST 2026 - Model qwen3.6:35b w/ 12 Thread(s), tokens/sec: 5.661822236694878 @ context=32000
Stopping all ollama usage... Stopping all ollama usage...
... Wed Oct 21 05:22:59 AM MST 2026 - qwen3.6:35b w/ 4 Thread(s), tokens/sec: 14.209790405591518 @ context=64000, 24 secs elapsed
Wed Oct 21 05:23:23 AM MST 2026 - qwen3.6:35b w/ 5 Thread(s), tokens/sec: 11.334255701323816 @ context=64000, 29 secs elapsed
Wed Oct 21 05:23:52 AM MST 2026 - qwen3.6:35b w/ 6 Thread(s), tokens/sec: 13.279266939258937 @ context=64000, 29 secs elapsed
Wed Oct 21 05:24:21 AM MST 2026 - qwen3.6:35b w/ 7 Thread(s), tokens/sec: 14.27680090014006 @ context=64000, 21 secs elapsed
Wed Oct 21 05:24:42 AM MST 2026 - qwen3.6:35b w/ 8 Thread(s), tokens/sec: 13.99919128227428 @ context=64000, 25 secs elapsed
Stopping all ollama usage...
Wed Oct 21 05:29:50 AM MST 2026 - qwen3.6:35b w/ 4 Thread(s), tokens/sec: 13.478375923353315 @ context=96000, 28 secs elapsed
Wed Oct 21 05:30:18 AM MST 2026 - qwen3.6:35b w/ 5 Thread(s), tokens/sec: 12.90997320417067 @ context=96000, 23 secs elapsed
Wed Oct 21 05:30:41 AM MST 2026 - qwen3.6:35b w/ 6 Thread(s), tokens/sec: 12.956446350317137 @ context=96000, 23 secs elapsed
Wed Oct 21 05:31:05 AM MST 2026 - qwen3.6:35b w/ 7 Thread(s), tokens/sec: 13.93074896590209 @ context=96000, 22 secs elapsed
Wed Oct 21 05:31:26 AM MST 2026 - qwen3.6:35b w/ 8 Thread(s), tokens/sec: 12.688771917209992 @ context=96000, 22 secs elapsed
Stopping all ollama usage...
Wed Oct 21 05:36:08 AM MST 2026 - qwen3.6:35b w/ 4 Thread(s), tokens/sec: 11.971487833921072 @ context=128000, 23 secs elapsed
Wed Oct 21 05:36:31 AM MST 2026 - qwen3.6:35b w/ 5 Thread(s), tokens/sec: 12.704959054740291 @ context=128000, 24 secs elapsed
Wed Oct 21 05:36:55 AM MST 2026 - qwen3.6:35b w/ 6 Thread(s), tokens/sec: 11.484965120109196 @ context=128000, 28 secs elapsed
Wed Oct 21 05:37:23 AM MST 2026 - qwen3.6:35b w/ 7 Thread(s), tokens/sec: 11.957040482880984 @ context=128000, 30 secs elapsed
Wed Oct 21 05:37:53 AM MST 2026 - qwen3.6:35b w/ 8 Thread(s), tokens/sec: 10.165480245815742 @ context=128000, 27 secs elapsed
Stopping all ollama usage...
Wed Oct 21 05:44:05 AM MST 2026 - qwen3.6:35b w/ 4 Thread(s): , tokens/sec: 11.794151678144981 @ context=192000, time: 22 secs
Wed Oct 21 05:44:27 AM MST 2026 - qwen3.6:35b w/ 5 Thread(s): , tokens/sec: 13.191786678902528 @ context=192000, time: 30 secs
Wed Oct 21 05:44:57 AM MST 2026 - qwen3.6:35b w/ 6 Thread(s): , tokens/sec: 12.974118764961352 @ context=192000, time: 25 secs
Wed Oct 21 05:45:22 AM MST 2026 - qwen3.6:35b w/ 7 Thread(s): , tokens/sec: 13.684751495860636 @ context=192000, time: 22 secs
Wed Oct 21 05:41:57 AM MST 2026 - qwen3.6:35b w/ 0 Thread(s): , tokens/sec: 14.771664402476594 @ context=192000, time: 22 secs
Stopping all ollama usage...
Wed Oct 21 05:47:40 AM MST 2026 - qwen3.6:35b w/ 4 Thread(s): , tokens/sec: 11.75920993970465 @ context=256000, time: 25 secs
Wed Oct 21 05:48:06 AM MST 2026 - qwen3.6:35b w/ 5 Thread(s): , tokens/sec: 13.414819339156582 @ context=256000, time: 26 secs
Wed Oct 21 05:48:32 AM MST 2026 - qwen3.6:35b w/ 6 Thread(s): , tokens/sec: 12.512960121852013 @ context=256000, time: 31 secs
Wed Oct 21 05:49:03 AM MST 2026 - qwen3.6:35b w/ 7 Thread(s): , tokens/sec: 11.610753098619734 @ context=256000, time: 29 secs
Wed Oct 21 05:45:46 AM MST 2026 - qwen3.6:35b w/ 0 Thread(s): , tokens/sec: 12.81995869775592 @ context=256000, time: 23 secs
```
#### qwen3.5:35b
```console
$ for c in 32000 128000 256000; do ollama_threads qwen3.5:35b $c; done
Wed Oct 21 07:55:03 AM MST 2026 - qwen3.5:35b w/ 4 Thread(s): tokens/sec: 10.3573012564637 @ context=128000, time: 94 secs
Wed Oct 21 07:56:37 AM MST 2026 - qwen3.5:35b w/ 6 Thread(s): tokens/sec: 11.929392994980638 @ context=128000, time: 39 secs
Wed Oct 21 07:57:17 AM MST 2026 - qwen3.5:35b w/ 7 Thread(s): tokens/sec: 13.082804815917008 @ context=128000, time: 36 secs
Wed Oct 21 07:57:53 AM MST 2026 - qwen3.5:35b w/ 0 Thread(s): tokens/sec: 12.665376120429427 @ context=128000, time: 81 secs
``` ```
## RAM Usage by Context ## RAM Usage by Context
tasks/workstation/linux/software/llm.yml
+46 -10
View File
@@ -144,7 +144,17 @@
- { "purpose": ["code"], "model": "qwen2.5-coder:7b", "provider": "qwen_25_coder_0070", "size_mb": "{{ llm_size_coef * 4700 }}", "context": 32768 } - { "purpose": ["code"], "model": "qwen2.5-coder:7b", "provider": "qwen_25_coder_0070", "size_mb": "{{ llm_size_coef * 4700 }}", "context": 32768 }
- { "purpose": ["code"], "model": "qwen2.5-coder:14b", "provider": "qwen_25_coder_0140", "size_mb": "{{ llm_size_coef * 9000 }}", "context": 32768 } - { "purpose": ["code"], "model": "qwen2.5-coder:14b", "provider": "qwen_25_coder_0140", "size_mb": "{{ llm_size_coef * 9000 }}", "context": 32768 }
- { "purpose": ["code"], "model": "qwen2.5-coder:32b", "provider": "qwen_25_coder_0320", "size_mb": "{{ llm_size_coef * 20000 }}", "context": 32768 } - { "purpose": ["code"], "model": "qwen2.5-coder:32b", "provider": "qwen_25_coder_0320", "size_mb": "{{ llm_size_coef * 20000 }}", "context": 32768 }
##### Mistral, Ministral, and Devstral - By a French company? ##### ##### Mistral, Ministral, and Devstral - By a French company. #####
# mistral-small-4
# https://huggingface.co/unsloth/Mistral-Small-4-119B-2603-GGUF
# Supposed to be better than Qwen equivalents, it's basically mistral, mixtral, magistral, and devstral all in one.
# unsloth version is supposed to be the best quantization. UD-Q3_K_XL is supposed to take 64GB RAM, lol, while Q4_K_M would need 80+ GB.
# needs done via 'ollama create', fails with pull. https://github.com/ollama/ollama/issues/5245
- { "purpose": ["chat", "lang", "code"], "model": "hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q3_K_XL", "provider": "mistral_small40_1190_unsloth_q3", "size_mb": "{{ llm_size_coef * 54800 }}", "context": 256000 }
# https://huggingface.co/mistralai/Mistral-Small-4-119B-2603 : 242GB unquantized, lol.
- { "purpose": ["chat", "lang", "code"], "model": "hf.co/mistralai/Mistral-Small-4-119B-2603", "provider": "mistral_small40_1190", "size_mb": "{{ llm_size_coef * 242000 }}", "context": 256000 }
# https://huggingface.co/unsloth/Mistral-Small-4-119B-2603 : 121GB, A6B MoE, hmmm!
- { "purpose": ["chat", "lang", "code"], "model": "hf.co/unsloth/Mistral-Small-4-119B-2603", "provider": "mistral_small40_1190_unsloth_a6b", "size_mb": "{{ llm_size_coef * 121000 }}", "context": 256000 }
# https://ollama.com/library/devstral-small-2 : Last Updated 2025-12-13 # https://ollama.com/library/devstral-small-2 : Last Updated 2025-12-13
# Most recommended in Mistral family for agentic coding. # Most recommended in Mistral family for agentic coding.
- { "purpose": ["code"], "model": "devstral-small-2:24b", "provider": "mistral_dev20_0240_small", "size_mb": "{{ llm_size_coef * 15000 }}", "context": 393216 } - { "purpose": ["code"], "model": "devstral-small-2:24b", "provider": "mistral_dev20_0240_small", "size_mb": "{{ llm_size_coef * 15000 }}", "context": 393216 }
@@ -529,6 +539,7 @@
#!/bin/sh #!/bin/sh
exec 2>&1 exec 2>&1
image=ghcr.io/open-webui/open-terminal:latest image=ghcr.io/open-webui/open-terminal:latest
packages=""
# Wait for Docker to start up. # Wait for Docker to start up.
while [ ! -S /var/run/docker.sock ]; do sleep 1; done while [ ! -S /var/run/docker.sock ]; do sleep 1; done
@@ -547,6 +558,12 @@
echo "RUN: Updating..." echo "RUN: Updating..."
docker pull $image & docker pull $image &
if curl -sf --max-time 5 -o /dev/null https://hyperling.com; then
# Internet is available, pull extra packages. useful for having
# model compile Android apps, need to verify for Flutter.
packages="xz-utils libglu1-mesa libglu1-mesa ninja-build libnotify-bin libgtk-3-dev liblzma-dev libstdc++-12-dev libc6:amd64 libstdc++6 lib32z1 libbz2-1.0 default-jdk libncurses-dev android-udev-rules"
fi
# Start the open-terminal program. # Start the open-terminal program.
# https://github.com/open-webui/open-terminal#configuration # https://github.com/open-webui/open-terminal#configuration
set -e set -e
@@ -557,12 +574,10 @@
-v {{ user_user.home }}/Code:{{ user_user.home }}/Code \ -v {{ user_user.home }}/Code:{{ user_user.home }}/Code \
-e OPEN_TERMINAL_FILE_BROWSER_ROOT={{ user_user.home }} \ -e OPEN_TERMINAL_FILE_BROWSER_ROOT={{ user_user.home }} \
-e OPEN_TERMINAL_API_KEY={{ open_terminal_key }} \ -e OPEN_TERMINAL_API_KEY={{ open_terminal_key }} \
-e OPEN_TERMINAL_PACKAGES="$packages" \
$image run --port {{ open_terminal_port }} $image run --port {{ open_terminal_port }}
# -p {{ open_terminal_port }}:8000 # -p {{ open_terminal_port }}:8000
# This requires internet access to be successful...
#-e OPEN_TERMINAL_PACKAGES="xz-utils libglu1-mesa libglu1-mesa ninja-build libnotify-bin libgtk-3-dev liblzma-dev libstdc++-12-dev libc6:amd64 libstdc++6 lib32z1 libbz2-1.0 default-jdk libncurses-dev android-udev-rules" \
mode: "0755" mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | open-terminal | Script | Finish - name: Workstation | Linux | Software | LLMs | runit | open-terminal | Script | Finish
@@ -876,7 +891,7 @@
spacing="$sep %-${col1}s $sep %${col2}s $sep %${col3}s $sep %${col4}s $sep" spacing="$sep %-${col1}s $sep %${col2}s $sep %${col3}s $sep %${col4}s $sep"
#echo " Stopping all ollama usage..." #echo " Stopping all ollama usage..."
sudo sv restart ollama >/dev/null 2>&1 #sudo sv restart ollama >/dev/null 2>&1
#echo -e "\n Checking model disk and RAM sizes...\n" #echo -e "\n Checking model disk and RAM sizes...\n"
@@ -922,13 +937,33 @@
context=',"num_ctx":'$num_ctx'' context=',"num_ctx":'$num_ctx''
fi fi
echo " Stopping all ollama usage..." # Physical CPU Count (no longer using ansible_processor_vcpus, {{ ansible_processor_vcpus }})
sudo sv restart ollama >/dev/null 2>&1 # Will be something like 0-7, then get expanded to 0 1 2 3 4 5 6 7.
# Runnning with 0 causes default behavior, 1 per physical core, 8!
cores=$(cat /sys/devices/cpu_core/cpus | tr ',' '\n' | sed 's/-/ /' | xargs -L1 seq)
# Flatten the output (trims newlines and extra spacing).
cores=$(echo $cores)
# Take out useless tests. 1 CPU is silly. If we have 8 physical then
# only need to look at 4, 6, 7, and 8 (which is done by 0/default).
cores=${cores/ 1 / }
if [[ "$cores" == *" 7" ]]; then
cores=${cores/ 2 / }
cores=${cores/ 3 / }
cores=${cores/ 5 / }
fi
# Do the 0 test last.
cores="${cores/0 / } 0"
#echo " Stopping all ollama usage..."
#sudo sv restart ollama >/dev/null 2>&1
# Benchmark Thread Count # Benchmark Thread Count
for t in {1..{{ ansible_processor_vcpus | int }}}; do for t in $cores; do
start=$SECONDS start=$SECONDS
echo -n "`date` - Model $model w/ $t Thread(s): " echo -n "`date` - $model w/ $t Thread(s): "
speed=$(curl -s http://localhost:11434/api/generate \ speed=$(curl -s http://localhost:11434/api/generate \
-d '{"model":"'$model'","prompt":"Hello","stream":false,"keep_alive":1,"options":{"num_thread":'$t$context'}}' \ -d '{"model":"'$model'","prompt":"Hello","stream":false,"keep_alive":1,"options":{"num_thread":'$t$context'}}' \
@@ -938,7 +973,8 @@
ctx="`ollama ps | grep $model | awk '{print $7}'`" ctx="`ollama ps | grep $model | awk '{print $7}'`"
time=$(( $finish - $start )) time=$(( $finish - $start ))
echo ", tokens/sec: $speed @ context=$ctx, time: $time secs" #echo "tokens/sec: $speed @ context=$ctx, time: $time secs"
printf "%-32s %18s %16s\n" "tokens/sec: $speed" "@ context=$ctx," "time: $time secs"
ollama stop $model >/dev/null 2>&1 ollama stop $model >/dev/null 2>&1
done done