llm, add mistral-small and see it if't truly the v4 MoE.

tasks/workstation/linux/software/ai/llm.yml

@@ -164,6 +164,8 @@
           - { "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 }
+              # Supposedly ollama has it tagged at mistral-small with no params given. it's not on the site though. Let's find out!
+          - { "purpose": ["chat", "lang", "code"], "model": "mistral-small",                                           "provider": "mistral_small40_1190",             "size_mb": 60000                          , "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 }