Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Magistral — the first reasoning model by Mistral AI

mistral.ai

Post reply on HN
Print view View original

271–280 of 444 posts

Re: Magistral — the first reasoning model by Mistral AI

#271

Post by kgwgk »

Saline9515 wrote: post #235
kgwgk wrote: post #200

Earlier quoted context omitted.

> 50 hours+/week is not exceptionl. https://www.legifrance.gouv.fr/codes/article_lc/LEGIARTI0000... Au cours d'une même semaine, la durée maximale hebdomadaire de travail est de quarante-huit heures. https://www.legifrance.gouv.fr/codes/article_lc/LEGIARTI0000... La durée hebdomadaire de travail calculée sur une période quelconque de douze semaines consécutives ne peut dépasser quarante-quatre heures, sauf dans les c…

Everyone is "forfait cadre", which allow them to work with no practical time limit since they don't log their time spent at work. https://www.service-public.fr/particuliers/vosdroits/F19261

It seems that 20% of employees in the private sector are "cadres" and half of them are on "forfait jours". That makes around 10% of the private sector employees working 218 days per year without the 48/44 weekly hour limits. It's more than I thought but I doubt that many of them work more than 10 hours per day. Whether that's "exceptional" or not is a matter of definition, of course.

Re: Magistral — the first reasoning model by Mistral AI

#272

Post by trc001 »

Onavo wrote: post #64
danielhanchen wrote: post #29

Earlier quoted context omitted.

Their paper https://mistral.ai/static/research/magistral.pdf is also cool! They edited GRPO via: 1. Removed KL Divergence 2. Normalize by total length (Dr. GRPO style) 3. Minibatch normalization for advantages 4. Relaxing trust region

> Removed KL Divergence Wait, how are they computing the loss?

It's become trendy to delete it. I say trendy because many papers delete it without offering any proof that it is meaningless

Re: Magistral — the first reasoning model by Mistral AI

#273

Post by semi-extrinsic »

ozgune wrote: post #150
danielhanchen wrote: post #3

I 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…

Their benchmarks are interesting. They are comparing to DeepSeek-V3's (non-reasoning) December and DeepSeek-R1's January releases. I feel that comparing to DeepSeek-R1-0528 would be more fair. For example, R1 scores 79.8 on AIME 2024, R1-0528 performs 91.4. R1 scores 70 on AIME 2025, R1-0528 scores 87.5. R1-0528 does similarly better for GPQA Diamond, LiveCodeBench, and Aider (about 10-15 points higher). https://hugg…

Would also be interesting to compare with R1-0528-Qwen3-8B (chain-of-thought distilled from Deepseek-R1-0528 and post-trained into Qwen3-8B). It scores 86 and 76 on AIME 2024 and 2025 respectively.

Currently running the 6-bit XL quant on a single old RTX 2080 Ti and I'm quite impressed TBH. Simply wild for a sub-8GB download.

Re: Magistral — the first reasoning model by Mistral AI

#274

Post by bobxmax »

debugnik wrote: post #243
bobxmax wrote: post #160

Earlier quoted context omitted.

Rights and protections that have benefited heavily from an economy built on the alliance with the US. If it weren't for American help and trade post-WW2, Europe would be a Belarusian backwater and is fast heading back in that direction. Countries like Greece, Italy, Spain, Portugal, etc. show the future of Europe as it slowly stagnates and becomes a museum that can't feed it's people. Even Germany that was once excel…

> Countries like Greece, Italy, Spain, Portugal PIGS, really? Some of the top growing EU economies right now, which have turned their deficit around, show the future of a slowly stagnating Europe?

A 200B economy growing 2% is the future of the EU? Yes that is the point I am making.

Re: Magistral — the first reasoning model by Mistral AI

#275

Post by mark_l_watson »

Nice, and I see that Ollama already has the smaller 24B version. I am traveling with just a mobile device so I have to wait to try it, but I have been using their new devstral coding model and it is very useful, given that it is also a locally run model so I looking forward to trying magistral.

Re: Magistral — the first reasoning model by Mistral AI

#276

Post by bobsomers »

LordDragonfang wrote: post #269
cluckindan wrote: post #242

Earlier quoted context omitted.

It does not do any thinking. It is a statistical model, just like the rest of them.

"Thinking" is a term of art referring to the hidden/internal output of "reasoning" models where they output "chain of thought" before giving an answer[1]. This technique and name stem from the early observation that LLMs do better when explicitly told to "think step by step"[2]. Hope that helps clarify things for you for future constructive discussion. [1] https://arxiv.org/html/2410.10630v1 [2] https://arxiv.org/pdf…

We are aware of the term of art.

The point that was trying to be made, which I agree with, is that anthropomorphizing a statistical model isn’t actually helpful. It only serves to confuse laypersons into assuming these models are capable of a lot more than they really are.

That’s perfect if you’re a salesperson trying to dump your bad AI startup onto the public with an IPO, but unhelpful for pretty much any other reason, especially true understanding of what’s going on.

Re: Magistral — the first reasoning model by Mistral AI

#277

Post by snoman »

whiplash451 wrote: post #244
aDyslecticCrow wrote: post #231

Earlier quoted context omitted.

> It was worth the burn to capture the market. You cannot compare Uber to the AI market. They are too different. Uber captured the market because having three taxi services is annoying. But people are readily jumping between models using multi-model platforms. And nobody is significantly ahead of the pack. There is nothing that sets anyone apart aside from the rate at which they are burning capital. Any advantage is…

Three cab apps are a lot less annoying than three LLM apps each having their piece of your chats history. The winner-take-all effect is a lot stronger with chat apps.

That’s the exact opposite of the way it is right now (at least for me). I don’t like having multiple ride hailing apps but easily have ChatGPT, Claude, Gemini on my phone (and local LLM at home). There is zero effort cost to go from one to the other.

Re: Magistral — the first reasoning model by Mistral AI

#278

Post by bobxmax »

TulliusCicero wrote: post #247
baq wrote: post #173

Earlier quoted context omitted.

Europeans also mostly don’t suffer from school shootings and generally don’t go bankrupt when they get cancer or just take an ambulance ride to a non-network hospital. Regulation is not all bad, besides the US has more of it than anybody else.

The mental gymnastics here are incredible. Do you really think the regulations inhibiting tech startup creation are the same ones that protect people when they get cancer or whatever? Yes, the US has a lot of school shootings, but does anyone think loose gun regulations are why the US is strong on tech?

Any time European economic failings are brought up it's always the same thing. "Well at least no school shootings!"

Great, Singapore has less school shootings and homeless people than anywhere in Europe by a country mile and has a soaring economy.

Re: Magistral — the first reasoning model by Mistral AI

#279

Post by bobxmax »

camjw wrote: post #207
bobxmax wrote: post #155

Earlier quoted context omitted.

Because Europeans don't take smart risks. Because they over regulate. It's fascinating watching people circle back to this answer. Regulation and taxation reduces incentives. Lower incentives, means lower risk-taking. The fact this is still a lesson that needs to be debated is absurd.

I would love to know what you do for a living and whether you personally have taken any smart risks that have lead you to financial success, or whether you just like sniping on HN about school shootings and pretending to be superior.

[flagged]

Re: Magistral — the first reasoning model by Mistral AI

#280

Post by lolive »

nake13 wrote: post #14

The Magistral Small can fit within a single RTX 4090 or a 32GB RAM MacBook once quantized.

Is it indeed the plan of Apple to eventually run such kind of models direcly inside a iPhone? Or are the specs of any stateOfTheArt smartphone well below the minimum requirements of such "lightweight" models?
Post reply on HN