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

llm, attempt to fix decimal values which are supposed to be integers, fix some spacing.

Browse Source
This commit is contained in:
me
2026-10-09 15:26:22 -07:00
parent 816ef4ddc6
commit 9e6e162b03
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tasks/workstation/linux/software/llm.yml
+6 -6
View File
@@ -33,9 +33,9 @@
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 }}"
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 }}"
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:
@@ -79,10 +79,10 @@
- { "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}}" }
- { "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 }}" }