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

161–170 of 444 posts

Re: Magistral — the first reasoning model by Mistral AI

#161

Post by bobxmax »

int_19h wrote: post #134
MoonGhost wrote: post #90

Earlier quoted context omitted.

No, thanks, we don't want to be like EU. Everything regulated to death. They even thought to criminalize street photography because there could be copyrighted materials in the picture. Not sure, are they still taxing Eiffel tower images?

EU is not a monolithic entity, and amount of regulation varies widely. Baltics are very business friendly, for example.

And Estonia has the most impressive tech ecosystem on the continent while being a soviet backwater 20 years ago. Shocking how that works.

Re: Magistral — the first reasoning model by Mistral AI

#162

Post by gyrovagueGeist »

danielhanchen wrote: post #29
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 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

Does anyone know why they added minibatch advantage normalization (or when it can be useful)?

The paper they cite "What matters in on-policy RL" claims it does not lead to much difference on their suite of test problems, and (mean-of-minibatch)-normalization doesn't seem theoretically motivated for convergence to the optimal policy?

Re: Magistral — the first reasoning model by Mistral AI

#163

Post by rafram »

umbra07 wrote: post #138
kobe_bryant wrote: post #118

Earlier quoted context omitted.

it's bizarre. the first sentence is "Announcing Magistral — the first reasoning model by Mistral AI — excelling in domain-specific, transparent, and multilingual reasoning." and those should clearly be comma and this sentence is just flat out wrong "Lack of specialized depth needed for domain-specific problems, limited transparency, and inconsistent reasoning in the desired language — are just some of the known limit…

really? i would have written it the exact same way (with dashes instead of commas).

The second one is unambiguously wrong. The first just looks kind of weird.

Re: Magistral — the first reasoning model by Mistral AI

#165

Post by yorwba »

csomar wrote: post #100
saubeidl wrote: post #46

Earlier quoted context omitted.

As a counterexample, China's tech industry has caught up and in some ways surpassed the US, partially due to being closed off.

> As a counterexample, China's tech industry has caught up and in some ways surpassed the US, partially due to being closed off. How did you come up to that conclusion? We don't have access to an alternate universe where the Chinese tech market was open. There is a real possibility that it would have been far ahead had it been open.

We do have access to records from the before times when the internet was wide open and Facebook, Google and Microsoft were big in China. Well, Microsoft is still big because they're not an internet company and unfazed by censorship, but the exit of Google and Facebook took a lot of pressure off Baidu and the entire Chinese social media ecosystem.

Re: Magistral — the first reasoning model by Mistral AI

#166

Post by diggan »

atxtechbro wrote: post #147
simonw wrote: post #119

Here are my notes on trying this out locally via Ollama and via their API (and the llm-mistral plugin) too: https://simonwillison.net/2025/Jun/10/magistral/

Hi Simon, What's the huge difference between the two pelicans riding bicycles? Was one running locally the small version vs the pretty good one running the bigger one thru the API? Thanks, Morgan

Ollama doesn't like proper naming for some reason, so `ollama pull magistral:latest` lands you with the q4_K_M version (currently, subject to change).

Mistral's API defaults to `magistral-medium-2506` right now, which is running with full precision, no quantization.

Re: Magistral — the first reasoning model by Mistral AI

#167

Post by atemerev »

hshdhdhj4444 wrote: post #89
SV_BubbleTime wrote: post #75

Earlier quoted context omitted.

Ok, just a quick question… why does Europe not have the money actual/people?

Part of the answer is debt. The U.S. has a debt of 35Tn. The entire EU around 16Tn. If even 10% of the debt difference was invested in tech that would have meant about $2tn more in investment in EU tech.

The amount of debt you are allowed to take and the abundance of money to invest in new projects are in direct proportion to the competitiveness of the jurisdiction, i.e. business-friendly environment.

EU is not a business-friendly environment.

Re: Magistral — the first reasoning model by Mistral AI

#168

Post by Ringz »

thot_experiment wrote: post #113
a2128 wrote: post #109

Earlier quoted context omitted.

24B is the size of the Small opensourced model. The Medium model is bigger (they don't seem to disclose its size) and still gets beaten by Deepseek R1

Mistral Large is 123b so one can probably assume that medium is between 24b and 123b, also Mistral 3.1 is by a wide margin my go-to model in real life situations. Benchmarks absolutely don't tell the whole story, and different models have different use cases.

Can you please explain what your „real life situations“ are?

Re: Magistral — the first reasoning model by Mistral AI

#169

Post by diggan »

NitpickLawyer wrote: post #128
simonw wrote: post #117

Earlier quoted context omitted.

Tool calling isn't enabled in the official Magistral Small GGUF (or the Ollama one) which is sad. Hope they (or someone else) fix that soon.

They have already released Devstral, which is a tool-specific finetune of the same base model. That works pretty well with cline (even though it was specifically tuned for open-hands). This would likely be a good model for the "plan" mode in various agentic tools (cline, aider, cursor/windsurf/void, etc). So you'd have a chat in plan mode, then use devstral to actually implement that plan.

Devstral is targeting tool use+coding I think, so something like Magistral but also tool calling (during thinking) would be handy too, just for other use cases. But also beneficial in the context of creating plans for Devstral.

Re: Magistral — the first reasoning model by Mistral AI

#170

Post by atemerev »

Mistletoe wrote: post #71
atemerev wrote: post #15

Earlier quoted context omitted.

"EU is leading in regulation", they say. I don't know what they are thinking.

This is why I want to move to the EU. I don’t care if companies aren’t coddled there. I want to live where people are the first priority.

Well, are you ready to live on a low middle class salary of a European software engineer? It is really low middle class. The middle middle here would be a bank clerk, and upper middle — a lawyer or a surgeon.

This is not coincidental.

Post reply on HN