Magistral — the first reasoning model by Mistral AI
1–10 of 444 posts
Re: Magistral — the first reasoning model by Mistral AI
#2Good first shot i guess, but the small ones about as good as v3, and the mediums not quite as good as r1... i wonder if that r1 is the actual new one or the old one
Re: Magistral — the first reasoning model by Mistral AI
#3I made some GGUFs for those interested in running them at https://huggingface.co/unsloth/Magistral-Small-2506-GGUF
ollama run hf.co/unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
or
./llama.cpp/llama-cli -hf unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL --jinja --temp 0.7 --top-k -1 --top-p 0.95 -ngl 99
Please use --jinja for llama.cpp and use temperature = 0.7, top-p 0.95!
Also best to increase Ollama's context length to say 8K at least: OLLAMA_CONTEXT_LENGTH=8192 ollama serve &. Some other details in https://docs.unsloth.ai/basics/magistral
Re: Magistral — the first reasoning model by Mistral AI
#4Would be interesting to see a comparison with Qwen 32B. I found it a fantastic local model (ollama).
Re: Magistral — the first reasoning model by Mistral AI
#5A few days after Apple's "The illusion of Reasoning". I wonder if this is the same again. Anyone runs Tower of Hanoi?
Re: Magistral — the first reasoning model by Mistral AI
#6a bit too late aren't we??
Re: Magistral — the first reasoning model by Mistral AI
#7A few days after Apple's "The illusion of Reasoning". I wonder if this is the same again. Anyone runs Tower of Hanoi?
The Tower of Hanoi problem is limited by context length rather than model intelligence - see https://x.com/scaling01/status/1931783050511126954
Re: Magistral — the first reasoning model by Mistral AI
#8A few days after Apple's "The illusion of Reasoning". I wonder if this is the same again. Anyone runs Tower of Hanoi?
That paper was flawed in many ways, but it had a catchy name so lots of 'fluencers and media pounced on it and slopped some content based on the title alone. Chances are it will be relegated to the blooper section of LLM papers, just like that "training on LLM outputs leads to model collapse" paper was...
Re: Magistral — the first reasoning model by Mistral AI
#9A few days after Apple's "The illusion of Reasoning". I wonder if this is the same again. Anyone runs Tower of Hanoi?
The illussion of reasoning was terrible paper. 2^n-1 how it could fit in context size. I tried o3 and he gave me python script saying that inserting all moves is to much for context window. completely different results.
Re: Magistral — the first reasoning model by Mistral AI
#10Good first shot i guess, but the small ones about as good as v3, and the mediums not quite as good as r1... i wonder if that r1 is the actual new one or the old one
The Deepseek V3 is a model with 671 billion parameters, of which 37 billion are active.
Magistral Small is a 24 billion parameter model.
Pretty impressive in terms of efficiency for Mistral.
The size of the Magistral Medium is not publicly available, so it is difficult to compare efficiency there.