me/env-ansible
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
816ef4ddc6eec81cc274587c40be7cb18357a8d5
env-ansible/tasks/workstation/linux/software/llm.yml
T

441 lines
18 KiB
YAML
Raw Blame History

---
# 2026-10-05 Hyperling
# Install a local LLM for use offline.
# - https://zeroclaw.net/blog/install-zeroclaw
# - https://zeroclaw.net/blog/set-up-zeroclaw-bot-ollama-telegram
#
# Packages Details
# - https://archlinux.org/packages/extra/x86_64/zeroclaw/
# - https://archlinux.org/packages/extra/x86_64/ollama/
#
# Individual Guides
# - https://github.com/zeroclaw-labs/zeroclaw
# - https://wiki.archlinux.org/title/Ollama
#
# Model Explanations
# - https://webscraft.org/blog/ollama-na-8-gb-ram-yaki-modeli-pratsyuyut-u-2026?lang=en
#
# Models
# - https://ollama.com/search
#
# References
# - https://docs.zeroclaw.com/master/en/reference/config.html
# - https://docs.ollama.com
# Currently only testing this on Arch based distros (pacman).
- name: Workstation | Linux | Software | LLMs
block:
- name: Workstation | Linux | Software | LLMs | Facts 01
ansible.builtin.set_fact:
ollama: ollama
zeroclaw: zeroclaw
zerocode: zerocode
qwen_code: qwen-code
# Good to keep low to prevent swap usage.
llm_concurrency: "{{ ansible_memtotal_mb / 64000 | round(0, method='ceil') | int }}"
# Allow having multiple chats open without them just waiting each other.
llm_parallel: "{{ ansible_processor_vcpus / 8 | round(0, method='ceil') | int }}"
# Most LLMs take a coefficient of about 1.2 to 1.5 of their file size in
# RAM, which is usually less than guessing a usage of weight*1000.
# Example:
# - qwen3.5:9b would be 6.6GB * 1.3 = 8580, rather than 9000.
# Conversely:
# - qwen3.5:4b would be 3.3GB * 1.3 = 4290, rather than 4000.
llm_size_coef: 1.3
# Take the GB of RAM and use it as the MB of context.
llm_context: "{{ ansible_memtotal_mb | int }}"
- name: Workstation | Linux | Software | LLMs | Facts 02
ansible.builtin.set_fact:
ollama_runit_dir: "{{ runit_script_dir }}/{{ ollama }}"
ollama_runit_log_dest: "{{ global_log }}/{{ ollama }}"
zeroclaw_runit_dir: "{{ runit_script_dir }}/{{ zeroclaw }}"
zeroclaw_runit_log_dest: "{{ global_log }}/{{ zeroclaw }}"
- name: Workstation | Linux | Software | LLMs | Facts 03
ansible.builtin.set_fact:
ollama_runit_script: "{{ ollama_runit_dir }}/{{ runit_service_script }}"
ollama_runit_log_dir: "{{ ollama_runit_dir }}/{{ runit_log_dir }}"
ollama_runit_log_config: "{{ ollama_runit_log_dest }}/{{ global_log_config }}"
zeroclaw_runit_script: "{{ zeroclaw_runit_dir }}/{{ runit_service_script }}"
zeroclaw_runit_log_dir: "{{ zeroclaw_runit_dir }}/{{ runit_log_dir }}"
zeroclaw_runit_log_config: "{{ zeroclaw_runit_log_dest }}/{{ global_log_config }}"
- name: Workstation | Linux | Software | LLMs | Facts 04
ansible.builtin.set_fact:
ollama_runit_log_script: "{{ ollama_runit_log_dir }}/{{ runit_log_script }}"
zeroclaw_runit_log_script: "{{ zeroclaw_runit_log_dir }}/{{ runit_log_script }}"
- name: Workstation | Linux | Software | LLMs | Facts | LLMs
ansible.builtin.set_fact:
llm_installs: []
llm_removals:
- { "model": "qwen3:4b", "provider": "qwen_30_0040", "size_mb": 4000 }
- { "model": "qwen3.6:27b", "provider": "qwen_36_0270", "size_mb": 27000 }
- { "model": "qwen3.5:27b", "provider": "qwen_35_0270", "size_mb": "{{ llm_size_coef * 17000 }}" }
llm_choices:
### QWEN >3.5 - Need to try!
- { "model": "qwen3.8:27b", "provider": "qwen_38_0270", "size_mb": 27000 }
- { "model": "qwen3.6:35b", "provider": "qwen_36_0350", "size_mb": 35000 }
### QWEN 3.5 - Good for generic usage and a little coding.
- { "model": "qwen3.5:0.8b", "provider": "qwen_35_0008", "size_mb": "{{ llm_size_coef * 1200}}" }
- { "model": "qwen3.5:2b", "provider": "qwen_35_0020", "size_mb": "{{ llm_size_coef * 2700}}" }
- { "model": "qwen3.5:4b", "provider": "qwen_35_0040", "size_mb": "{{ llm_size_coef * 3300}}" }
- { "model": "qwen3.5:9b", "provider": "qwen_35_0090", "size_mb": "{{ llm_size_coef * 6600}}" }
# skip 27b and use 35b
- { "model": "qwen3.5:35b", "provider": "qwen_35_0350", "size_mb": "{{ llm_size_coef * 22000 }}" }
- { "model": "qwen3.5:122b", "provider": "qwen_35_1220", "size_mb": "{{ llm_size_coef * 81000 }}" }
### QWEN 3.0 Coder - Supposed to be better than 2.5 for machines that can handle it.
- { "model": "qwen3-coder:30b", "provider": "qwen_30_coder_0300", "size_mb": "{{ llm_size_coef * 19000 }}" }
- { "model": "qwen3-coder:420b", "provider": "qwen_30_coder_4200", "size_mb": "{{ llm_size_coef * 290000 }}" }
### QWEN 2.5 Coder - Ol'reliable!
- { "model": "qwen2.5-coder:0.5b", "provider": "qwen_25_coder_0005", "size_mb": "{{ llm_size_coef * 398 }}" }
- { "model": "qwen2.5-coder:1.5b", "provider": "qwen_25_coder_0015", "size_mb": "{{ llm_size_coef * 986 }}" }
- { "model": "qwen2.5-coder:3b", "provider": "qwen_25_coder_0030", "size_mb": "{{ llm_size_coef * 1900 }}" }
- { "model": "qwen2.5-coder:7b", "provider": "qwen_25_coder_0070", "size_mb": "{{ llm_size_coef * 4700 }}" }
- { "model": "qwen2.5-coder:14b", "provider": "qwen_25_coder_0140", "size_mb": "{{ llm_size_coef * 9000 }}" }
- { "model": "qwen2.5-coder:32b", "provider": "qwen_25_coder_0320", "size_mb": "{{ llm_size_coef * 20000 }}" }
### Mistral, Ministral, and Devstral - By a French company?
- { "model": "devstral-small-2:24b", "provider": "devstral_20_0240_small", "size_mb": 24000 }
#- mistral:7b
#- ministral-3:3b
#- ministral-3:8b
#- ministral-3:14b
##### TBD #####
### QWEN 2.5 - Older, but does not have "thinking", tempting!
#- qwen2.5:0.5b
#- qwen2.5:1.5b
#- qwen2.5:3b
#- qwen2.5:7b
#- qwen2.5:14b
#- qwen2.5:32b
#- qwen2.5:72b
### Z.ai
#- GLM-5.x
#- glm4-flash
### Others
#- deepseek-r1:1.5b
#- deepseek-r1:7b
- name: Workstation | Linux | Software | LLMs | Facts | Merge | Print
ansible.builtin.debug:
var: "{{ item }}"
loop:
- ansible_processor_vcpus
- ansible_memtotal_mb
- llm_concurrency
- llm_parallel
- llm_installs
- llm_removals
- llm_choices
- name: Workstation | Linux | Software | LLMs | Facts | Choices | Sort
ansible.builtin.set_fact:
llm_installs: >-
{{ llm_choices | selectattr('size_mb', 'le', ansible_memtotal_mb) | list }}
llm_removals: >-
{{ llm_choices | selectattr('size_mb', 'gt', ansible_memtotal_mb) | list }}
- name: Workstation | Linux | Software | LLMs | Facts | Merge | Print
ansible.builtin.debug:
var: "{{ item }}"
loop:
- llm_installs
- llm_removals
- name: Workstation | Linux | Software | LLMs | Packages | Install
ansible.builtin.package:
name:
- "{{ zeroclaw }}"
- "{{ ollama }}"
- "{{ zerocode }}"
- "{{ qwen_code }}"
state: present
- name: Workstation | Linux | Software | LLMs | runit
block:
- name: Workstation | Linux | Software | LLMs | runit | ollama | Dir | Run
ansible.builtin.file:
name: "{{ ollama_runit_dir }}"
state: directory
owner: root
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | ollama | Dir | Log Run
ansible.builtin.file:
name: "{{ ollama_runit_log_dir }}"
state: directory
owner: root
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | ollama | Dir | Log Config
ansible.builtin.file:
name: "{{ ollama_runit_log_dest }}"
state: directory
owner: "{{ user }}"
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | ollama | Script | Run
ansible.builtin.copy:
dest: "{{ ollama_runit_script }}"
content: |
#!/bin/sh -e
# Allow pulling LLMs for use with ZeroClaw.
exec 2>&1
export HOME={{ user_user.home }}
# Timeouts #
export OLLAMA_LOAD_TIMEOUT=20m # default is 5m
export OLLAMA_REQUEST_TIMEOUT=3600 # default 300 (unconfirmed, not in the list of --help vars)
# Resource Usage #
export OLLAMA_KEEP_ALIVE=20m # default is 5m
export OLLAMA_MAX_LOADED_MODELS={{ llm_concurrency }} # default is 3 if using CPUs, or 3 * NumGPUs
export OLLAMA_NUM_PARALLEL={{ llm_parallel }} # default is 1 and applies per-model (unconfirmed)
export OLLAMA_CONTEXT_LENGTH={{ llm_context }} # default is 4096, https://docs.ollama.com/faq#how-can-i-specify-the-context-window-size
export OLLAMA_MAX_QUEUE=999 # default is 512 (unconfirmed)
exec chpst -u {{ user }} ollama serve
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | ollama | Script | Log
ansible.builtin.copy:
dest: "{{ ollama_runit_log_script }}"
content: |
#!/bin/sh -e
exec svlogd -tt {{ ollama_runit_log_dest }}
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | ollama | Script | Log Config
ansible.builtin.copy:
dest: "{{ ollama_runit_log_config }}"
content: |
s10000000 # rotate at 10 MB
n5 # keep 5 old files
dateformat %Y-%m-%d_%H-%M-%S # each run gets its own file.
owner: "{{ user }}"
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | zeroclaw | Dir | Run
ansible.builtin.file:
name: "{{ zeroclaw_runit_dir }}"
state: directory
owner: root
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | zeroclaw | Dir | Log
ansible.builtin.file:
name: "{{ zeroclaw_runit_log_dir }}"
state: directory
owner: root
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | zeroclaw | Dir | Log Config
ansible.builtin.file:
name: "{{ zeroclaw_runit_log_dest }}"
state: directory
owner: "{{ user }}"
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | zeroclaw | Script | File
ansible.builtin.copy:
dest: "{{ zeroclaw_runit_script }}"
content: |
#!/bin/sh -e
# Allow using the ZeroClaw frontend.
exec 2>&1
export HOME={{ user_user.home }}
export SHELL={{ bash_exec.stdout }}
exec chpst -u {{ user }} zeroclaw daemon -v --log-level info
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | zeroclaw | Script | Log
ansible.builtin.copy:
dest: "{{ zeroclaw_runit_log_script }}"
content: |
#!/bin/sh -e
exec svlogd -tt {{ zeroclaw_runit_log_dest }}
mode: "0755"
- name: Workstation | Linux | Software | LLMs | runit | zeroclaw | Script | Log Config
ansible.builtin.copy:
dest: "{{ zeroclaw_runit_log_config }}"
content: |
s1000000 # rotate at 1 MB
n5 # keep 5 old files
dateformat %Y-%m-%d_%H-%M-%S # each run gets its own file.
mode: "0755"
when: ansible_service_mgr == "runit"
- name: Workstation | Linux | Software | LLMs | Services | Enable
ansible.builtin.service:
name: "{{ item }}"
state: started
enabled: true
loop:
- "{{ ollama }}"
- "{{ zeroclaw }}"
- name: Workstation | Linux | Software | LLMs | Services | Verify
ansible.builtin.uri:
url: "{{ item }}"
status_code: 200
timeout: 5
register: health
until: health.status == 200
retries: 12
delay: 5
loop:
- http://127.0.0.1:11434/
- http://127.0.0.1:42617/health
#- name: Workstation | Linux | Software | LLMs | Config | zeroclaw | Root
# ansible.builtin.blockinfile:
# path: "{{ user_user.home }}/.zeroclaw/config.toml"
# marker: "# {mark} ANSIBLE MANAGED BLOCK | zeroclaw | Defaults"
# insertbefore: '(?m)^schema_version'
# block: |
# default_provider = "ollama"
# default_model = "qwen3.5:4b"
# provider_timeout_secs = 3600
# state: present
# create: false
# backup: true
#- name: Workstation | Linux | Software | LLMs | Config | zeroclaw | Channels | header
# ansible.builtin.lineinfile:
# path: "{{ user_user.home }}/.zeroclaw/config.toml"
# insertbefore: '(?m)^[channels]'
# block: |
# message_timeout_secs = 3600
# state: present
# create: false
# backup: true
#- name: Workstation | Linux | Software | LLMs | Config | zeroclaw | Channels
# ansible.builtin.blockinfile:
# path: "{{ user_user.home }}/.zeroclaw/config.toml"
# marker: "# {mark} ANSIBLE MANAGED BLOCK | zeroclaw | Channels"
# insertbefore: '(?m)^[channels]'
# block: |
# message_timeout_secs = 3600
# state: present
# create: false
# backup: true
- name: Workstation | Linux | Software | LLMs | Models | ollama | Manual Script
ansible.builtin.blockinfile:
path: "{{ user_user.home }}/{{ item }}"
marker: "# {mark} ANSIBLE MANAGED BLOCK | ollama | Manual Script"
content: |
function pull_llms() {
echo "Manually Pulling Models"
{% for llm in llm_installs %}
echo -e "\n\n Starting {{ llm.model }} \n\n"
ollama pull {{ llm.model }} || {
status=$?
echo "ERROR: Pull failed with status $status, exiting."
exit $status
}
{% endfor %}
echo "Done!!"
}
alias pull-llms="pull_llms "
alias pull-models="pull_llms "
alias pull-ai="pull_llms "
state: present
create: false
backup: true
loop:
- .bashrc
- .zshrc
- name: Workstation | Linux | Software | LLMs | Models | ollama | Manual Script | Message
ansible.builtin.debug:
msg: |
The next task may take hours, if not days. if you'd a status bar,
I highly recommed reloading your RC file and running `pull-models`.
That will give you a much better idea of what's going on.
- name: Workstation | Linux | Software | LLMs | Models | ollama | Install
ansible.builtin.shell: |
set -o pipefail
item='{{ item.model }}'
if ollama list | grep -q $item; then
echo "OKAY" &&
return
else
ollama pull $item 1>/dev/null &&
echo "INSTALLED" &&
return
fi
echo "FAILED"
loop: "{{ llm_installs }}"
register: shell_check
changed_when: "'INSTALLED' in shell_check.stdout"
failed_when: "'FAILED' in shell_check.stdout"
become: true
become_user: "{{ user }}"
when: llm_installs | length > 0
- name: Workstation | Linux | Software | LLMs | Models | ollama | Remove
ansible.builtin.shell: |
set -o pipefail
item='{{ item.model }}'
if ollama list | grep -q $item; then
ollama rm $item &&
echo "INSTALLED" &&
return
else
echo "OKAY" &&
return
fi
echo "FAILED"
loop: "{{ llm_removals }}"
register: shell_check
changed_when: "'INSTALLED' in shell_check.stdout"
failed_when: "'FAILED' in shell_check.stdout"
become: true
become_user: "{{ user }}"
when: llm_removals | length > 0
# Cheat Sheet: https://docs.zeroclaw.com/master/en/providers/configuration.html
- name: Workstation | Linux | Software | LLMs | Models | zeroclaw | Add Providers
ansible.builtin.blockinfile:
path: "{{ user_user.home }}/.zeroclaw/config.toml"
marker: "# {mark} ANSIBLE MANAGED BLOCK | zeroclaw | Providers"
insertafter: EOF
block: |
{% for llm in llm_installs %}
[providers.models.ollama.{{ llm.provider }}]
model = "{{ llm.model }}"
timeout_secs = 3600 # 1 hour, default is 120 (2 minutes), issue happens between 5 and 6 minutes though.
context_window = {{ llm_context }}
{% endfor %}
state: present
create: false
backup: true
- name: Workstation | Linux | Software | LLMs | Models | Continue | Config
ansible.builtin.copy:
dest: "{{ user_user.home }}/.continue/config.yml"
content: |
# Maintained by `env-ansible/tasks/workstation/linux/software/llm.yml`
name: Main Config
version: 1.0.0
schema: v1
models:
{% for llm in llm_installs %}
- name: {{ llm.provider }}
provider: ollama
model: {{ llm.model }}
defaultCompletionOptions:
contextLength: {{ llm_context }}
maxTokens: {{ llm_context }}
{% endfor %}
mode: "0644"
when: ansible_pkg_mgr == "pacman"
Reference in New Issue View Git Blame Copy Permalink