From 9e6e162b03404761f0ba496d26faad0dc5bd8d20 Mon Sep 17 00:00:00 2001 From: Hyperling Date: Fri, 9 Oct 2026 15:26:22 -0700 Subject: [PATCH] llm, attempt to fix decimal values which are supposed to be integers, fix some spacing. --- tasks/workstation/linux/software/llm.yml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tasks/workstation/linux/software/llm.yml b/tasks/workstation/linux/software/llm.yml index 328a548..1602c91 100644 --- a/tasks/workstation/linux/software/llm.yml +++ b/tasks/workstation/linux/software/llm.yml @@ -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 }}" }