Merge branch 'dev2' into dev
Pushed on a system when another system still needed to push.
This commit is contained in:
me committed
commit
0363aefc1d
6 files changed
+297
-97
No files matched your search
@@ -68,6 +68,7 @@
|
||||
- "{{ alsa }}"
|
||||
- "{{ stress }}"
|
||||
- "{{ jq }}"
|
||||
- "{{ btop }}"
|
||||
state: present
|
||||
|
||||
- name: General | Software | Packages | Install Software (DEV)
|
||||
|
||||
@@ -103,11 +103,28 @@ TBD
|
||||
|
||||
#### 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
|
||||
|
||||
#### 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
|
||||
|
||||
@@ -116,83 +133,162 @@ TBD
|
||||
```console
|
||||
$ ollama-cpu qwen3.8:27b
|
||||
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 04:43:28 AM MST 2026 - Model qwen3.8:27b w/ 2 Thread(s), tokens/sec: 1.6705309718150672 @ 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 04:44:54 AM MST 2026 - Model qwen3.8:27b w/ 4 Thread(s), tokens/sec: 2.024676406965962 @ 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 04:46:19 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
|
||||
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 04:45:39 AM MST 2026 - qwen3.8:27b w/ 5 Thread(s), tokens/sec: 2.0480156821567044 @ 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 04:46:58 AM MST 2026 - qwen3.8:27b w/ 7 Thread(s), tokens/sec: 2.4228105619148526 @ context=257000
|
||||
Wed Oct 21 04:47:36 AM MST 2026 - qwen3.8:27b w/ 8 Thread(s), tokens/sec: 2.472564250465107 @ context=257000
|
||||
```
|
||||
|
||||
```console
|
||||
$ ollama-cpu qwen3.8:27b 32000
|
||||
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 04:55:29 AM MST 2026 - Model qwen3.8:27b w/ 2 Thread(s), tokens/sec: 1.388676019472746 @ 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 04:56:51 AM MST 2026 - Model qwen3.8:27b w/ 4 Thread(s), tokens/sec: 1.9083129860906882 @ 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 04:58:00 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
|
||||
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 04:57:30 AM MST 2026 - qwen3.8:27b w/ 5 Thread(s), tokens/sec: 2.727908205888872 @ 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 04:58:35 AM MST 2026 - qwen3.8:27b w/ 7 Thread(s), tokens/sec: 2.6835810717324833 @ context=32000
|
||||
Wed Oct 21 04:59:04 AM MST 2026 - qwen3.8:27b w/ 8 Thread(s), tokens/sec: 2.5231895597861493 @ context=32000
|
||||
```
|
||||
|
||||
#### 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
|
||||
|
||||
```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
|
||||
```
|
||||
|
||||
#### 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
|
||||
|
||||
#### qwen3.6:35b
|
||||
|
||||
Tests WAY faster than the dense models. Context does not seem to affect timing.
|
||||
|
||||
```console
|
||||
$ for c in 16000 32000 64000 96000 128000 192000 256000; do ollama_threads qwen3.6:35b $c; done
|
||||
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 05:03:37 AM MST 2026 - Model qwen3.6:35b w/ 2 Thread(s), tokens/sec: 10.940551196032734 @ 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 05:04:37 AM MST 2026 - Model qwen3.6:35b w/ 4 Thread(s), tokens/sec: 14.679419453925597 @ 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 05:05:43 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
|
||||
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 05:05:11 AM MST 2026 - qwen3.6:35b w/ 5 Thread(s), tokens/sec: 13.831044087619176 @ 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 05:06:09 AM MST 2026 - qwen3.6:35b w/ 7 Thread(s), tokens/sec: 14.603026210396049 @ context=16000
|
||||
Wed Oct 21 05:06:37 AM MST 2026 - qwen3.6:35b w/ 8 Thread(s), tokens/sec: 14.376794631809172 @ context=16000
|
||||
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 05:10:28 AM MST 2026 - Model qwen3.6:35b w/ 2 Thread(s), tokens/sec: 10.676325434530082 @ 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 05:11:39 AM MST 2026 - Model qwen3.6:35b w/ 4 Thread(s), tokens/sec: 13.683089387469174 @ 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 05:12:31 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
|
||||
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 05:12:04 AM MST 2026 - qwen3.6:35b w/ 5 Thread(s), tokens/sec: 13.447667625607968 @ 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 05:12:57 AM MST 2026 - qwen3.6:35b w/ 7 Thread(s), tokens/sec: 13.448480713710353 @ context=32000
|
||||
Wed Oct 21 05:13:27 AM MST 2026 - qwen3.6:35b w/ 8 Thread(s), tokens/sec: 13.143672445847205 @ context=32000
|
||||
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
|
||||
|
||||
@@ -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: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 }
|
||||
##### 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
|
||||
# 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 }
|
||||
@@ -529,6 +539,7 @@
|
||||
#!/bin/sh
|
||||
exec 2>&1
|
||||
image=ghcr.io/open-webui/open-terminal:latest
|
||||
packages=""
|
||||
|
||||
# Wait for Docker to start up.
|
||||
while [ ! -S /var/run/docker.sock ]; do sleep 1; done
|
||||
@@ -547,6 +558,12 @@
|
||||
echo "RUN: Updating..."
|
||||
docker pull $image &
|
||||
|
||||
if curl -sf --max-time 5 -o /dev/null https://hyperling.com; then
|
||||
# Internet is available, pull extra packages. useful for having
|
||||
# model compile Android apps, need to verify for Flutter.
|
||||
packages="xz-utils libglu1-mesa libglu1-mesa ninja-build libnotify-bin libgtk-3-dev liblzma-dev libstdc++-12-dev libc6:amd64 libstdc++6 lib32z1 libbz2-1.0 default-jdk libncurses-dev android-udev-rules"
|
||||
fi
|
||||
|
||||
# Start the open-terminal program.
|
||||
# https://github.com/open-webui/open-terminal#configuration
|
||||
set -e
|
||||
@@ -557,12 +574,10 @@
|
||||
-v {{ user_user.home }}/Code:{{ user_user.home }}/Code \
|
||||
-e OPEN_TERMINAL_FILE_BROWSER_ROOT={{ user_user.home }} \
|
||||
-e OPEN_TERMINAL_API_KEY={{ open_terminal_key }} \
|
||||
-e OPEN_TERMINAL_PACKAGES="$packages" \
|
||||
$image run --port {{ open_terminal_port }}
|
||||
|
||||
# -p {{ open_terminal_port }}:8000
|
||||
|
||||
# This requires internet access to be successful...
|
||||
#-e OPEN_TERMINAL_PACKAGES="xz-utils libglu1-mesa libglu1-mesa ninja-build libnotify-bin libgtk-3-dev liblzma-dev libstdc++-12-dev libc6:amd64 libstdc++6 lib32z1 libbz2-1.0 default-jdk libncurses-dev android-udev-rules" \
|
||||
mode: "0755"
|
||||
|
||||
- name: Workstation | Linux | Software | LLMs | runit | open-terminal | Script | Finish
|
||||
@@ -876,7 +891,7 @@
|
||||
spacing="$sep %-${col1}s $sep %${col2}s $sep %${col3}s $sep %${col4}s $sep"
|
||||
|
||||
#echo " Stopping all ollama usage..."
|
||||
sudo sv restart ollama >/dev/null 2>&1
|
||||
#sudo sv restart ollama >/dev/null 2>&1
|
||||
|
||||
#echo -e "\n Checking model disk and RAM sizes...\n"
|
||||
|
||||
@@ -922,13 +937,33 @@
|
||||
context=',"num_ctx":'$num_ctx''
|
||||
fi
|
||||
|
||||
echo " Stopping all ollama usage..."
|
||||
sudo sv restart ollama >/dev/null 2>&1
|
||||
# Physical CPU Count (no longer using ansible_processor_vcpus, {{ ansible_processor_vcpus }})
|
||||
# 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
|
||||
for t in {1..{{ ansible_processor_vcpus | int }}}; do
|
||||
for t in $cores; do
|
||||
start=$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 \
|
||||
-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 $7}'`"
|
||||
time=$(( $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
|
||||
done
|
||||
|
||||
Reference in new issue
Block a user