HN Reader

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 to say 8K at least: OLLAMA_CONTEXT_LENGTH=8192 ollama serve &. Some other details in https://docs.unsloth.ai/basics/magistral

Benchmarks suggest this model loses to Deepseek-R1 in every one-shot comparison. Considering they were likely not even pitting it against the newer R1 version (no mention of that in the article) and at more than double the cost, this looks like the best AI company in the EU is struggling to keep up with the state-of-the-art.

Their OCR model was really well hyped and coincidentally came out at the time I had a batch of 600 page pdfs to OCR. They were all monospace text just for some reason the OCR was missing.

I tried it, 80% of the "text" was recognised as images and output as whitespace so most of it was empty. It was much much worse than tesseract.

A month later I got the bill for that crap and deleted my account.

Maybe this is better but I'm over hype marketing from mistral

We just tested magistral-medium as a replacement for o4-mini in a user-facing feature that relies on JSON generation, where speed is critical. Depending on the complexity of the JSON, o4-mini runs ranged from 50 to 70 seconds. In our initial tests, Mistral returned results in 34–37 seconds. The output quality was slightly lower but still remain acceptable for us. We’ll continue testing, but the early results are promising. I'm glad to see Mistral prioritizing speed over raw power, there’s definitely a need for that.

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/

I don't understand why the benchmark selections are so scattered and limited. It only compares Magistral Medium with Deepseek V3, R1, and the other close weighted Mistral Medium 3. Why did they leave off Magistral Small entirely, alongside comparisons with Alibaba Qwen or the mini versions of o3 and o4?

I wished the charts included Qwen3, the current SOTA in reasoning.

Qwen3-4B almost beats Magistral-22B on the 4 available benchmarks, and Qwen3-30B-A3B is miles ahead.

As a quick test of logical reasoning and basic Wikipedia-level knowledge, I asked Mistral AI the following question:

A Brazilian citizen is flying from Sao Paulo to Paris, with a connection in Lisbon. Does he need to clear immigration in Lisbon or in Paris or in both cities or in neither city?

Mistral AI said that "immigration control will only be cleared in Paris," which I think is wrong.

After I pointed it to the Wikipedia article on this topic[1], it corrected itself to say that "immigration control will be cleared in Lisbon, the first point of entry into the Schengen Area."

I tried the same question with Meta AI (Llama 4) and it did much worse: It said that the traveler "wouldn't need to clear immigration in either Lisbon or Paris, given the flight connections are within the Schengen Area", which is completely incorrect.

I'd be interested to hear if other LLMs give a correct answer.

[1] https://en.wikipedia.org/wiki/Schengen_Area#Air_travel

Is the number of em-dashes in this marketing copy indicative of the kind of output that the model produces? If so, might want to tone it down a bit.

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

This doesn't really explain what "reasoning" means in the context of genAI, or how it's done by this product. Are there any good sources to learn more about what "reasoning model" means outside of marketing-speak?

Etymological fun: both "mistral" and "magistral" mean "masterly."

Mistral comes from Occitan for masterly, although today as far as I know it's only used in English when talking about mediterranean winds.

Magistral is just the adjective form of "magister," so "like a master."

If you want to make a few bucks, maybe look up some more obscure synonyms for masterly and pick up the domain names.

How many other open-weights reasoning models are there?

Is it possible to run multiple reasoning models on one problem? (Why not? I guess).

Another funny thought is: they release their Small model, and kept their Medium as a premium service. I wonder if you could do chains with Medium run occasionally, linked together by local runs of Small?

One cool think about this model, that I installed locally is that supports well other languages as well as it should be pleasant conversation partner.

BTW I am personally fan of Mistral, because while it is not the top model, it produces good results and the most important thing is that it is super fast, just go to it's chat and be amazed. It really saves a lot of time to have quick response.

The only mention of tools I could find is this:

> it significantly improves project planning, backend architecture, frontend design, and data engineering through sequenced, multi-step actions involving external tools or API.

I'm guessing this means it was trained with tool calling? And if so, does that mean it does tool calling within the thinking/reasoning, or within the main text? Seems unclear

Fully open reasoning traces are useful. Happy there is a vendor out there shipping that feature.

The featured accuracy benchmarks exclude every model that matter except DeepSeek, which is quite telling about this new model's performance.

This makes it yet another example of European companies building great products but fumbling marketing.

Mistral's edge is speed. It's a real pleasure to use because it answers in ~1s what takes other models 5-8s, which makes for a much better experience. But instead of focusing on it, they bury it far down the post.

Try it and see if you like the speed! Note that the speed advantage only applies to queries that don't require web-search, as Mistral is significantly slower on this one, leading to a ~5 seconds advantage over 2 minutes of research for the queries I benchmarked with Grok.

Good 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

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.

Below are my comments on Magistral small (not medium).

24B size is good for local inference.

As a model outputting long "reasoning" traces (~10k tokens), 40k context length is a little concerning.

Where are the results of normal benchmarks, e.g., MMLU/pro, IFEval and such.

Still, thank you Mistral team for releasing this model with Apache 2.0.

So, worse than R1, and only 24B version is open weights? NGMI. R1 is awesome, and full 630B version is open.

The RL algorithm used in Magistral is the same as the Reinforce++-baseline in OpenRLHF.

So, is it accessible in Le Chat?

Nice job!

Ah yes, the circle jerk of HN focuses not on technology or news but how "Europe falls behind". Mods are silent as always.

good

a bit too late aren't we??

A few days after Apple's "The illusion of Reasoning". I wonder if this is the same again. Anyone runs Tower of Hanoi?

One immediate observation I have about this model is that it seems to do a better job of filtering out or toning down some ideological disinformation that other models regurgitate from activist controlled Wikipedia articles, at least for a few I've checked. Previously you had to write your own sanity-check prompts to get the model to do extra up-front work to validate the logical and historical accuracy of things before it spits out what it thinks is the most popular answer.

With this, at least it seems like some of that work was done upfront or the thinking is tuned to avoid those issues, because it's giving me similar conclusions to a sanity-checked prompt. Heck, even Google Gemini and ChatGPT were spitting that stuff out, where this one is giving me a reasonable response. So in that regard, big thumbs up to the Mistral team if they did any specific work in that area. It's something I cared about that I was getting concerned nobody else cared about enough to fix.

I asked it my standard quest "Who was Adolf Hitler's mother?" and it's been bouncing between her married name and her maiden name, and it's still going! ollama run hf.co/unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL

>>> Who was Adolf Hitler's mother? <think> Alright, I know that Adolf Hitler is one of the most well-known historical figures, but I'm not entirely sure about his mother's name. I recall that his father was Alois Hitler, but I'm not sure about his mother. Maybe I can break this down.

First, I remember that Hitler was born in Austria, and his family background is often discussed in historical contexts. I think his mother was a local woman, but I don't recall her name. Maybe I can think about common names or try to recall if I've seen her name in documentaries or books.

I think I remember that his mother's name was Klara. But I'm not sure about the last name. Was it the same as his father's? Probably, since it was a common practice at the time for women to take their husband's surnames. But I'm not sure if that was the case here.

Wait, I recall that his father's name was Alois Hitler, and his mother's name was Klara. But what was her full name? I think it was Klara Hitler. But I'm not sure if she had a different last name before marriage.

I think I remember that her maiden name was Pölzl. But I'm not sure. I recall that she was from a lower-middle-class family, and that might be relevant.

But to be sure, I should think about the most common information. The most commonly cited name for Hitler's mother is Klara Hitler (née Pölzl). But is that accurate? I think so.

But to confirm, I recall that Klara Pölzl was her name before marriage, and after marrying Alois Hitler, she became Klara Hitler. But I'm not sure if that's correct.

Wait, I think I recall that his mother's name was Klara Hitler, but her maiden name was Klara Pölzl. But I'm not sure. Maybe I can think about the timeline.

Adolf Hitler was born in 1889. His mother must have been born some years before that. If she was in her early 20s when she had Adolf, she might have been born around the early 1860s.

But I don't have exact dates, so maybe I should focus on the name. I think the most common reference is Klara Hitler.

But I recall that in some sources, she is referred to as Klara Pölzl, especially when talking about her early life.

But in most historical references, she is known as Klara Hitler after marriage.

But I think the question is about her name, and it's common to refer to women by their married name in historical contexts, especially if that's the name they were most commonly known by.

So, her name was likely Klara Hitler.

But to be thorough, I think her full name was Klara Hitler (née Pölzl).

But the question asks for her name, and it's common to refer to someone by their married name, especially if that's the name they were most commonly associated with.

So, the answer is likely Klara Hitler.

But I recall that sometimes she is referred to as Klara Pölzl, especially in contexts where her maiden name is relevant.

But in general, historical references often use her married name.

I think the most accurate answer is Klara Hitler.

But to be sure, I recall that in many biographies, she is referred to as Klara Hitler.

Therefore, I think the answer is Klara Hitler.

But I'm not entirely confident. Maybe I can think of another way to verify this.

I recall that Hitler had a close relationship with his mother, and she is often mentioned in his early life. The name Klara Hitler seems to be the standard reference.

Therefore, I conclude that Adolf Hitler's mother was Klara Hitler.

But just to double-check, I think her maiden name was Pölzl, but she became Klara Hitler after marriage.

So, her name was Klara Hitler.

But sometimes people refer to her by her maiden name, especially in contexts where her family background is important.

But the most common and likely correct answer is Klara Hitler.

But I recall that in some sources, she is referred to as Klara Pölzl.

But in most standard references, it's Klara Hitler.

Therefore, I think the answer is Klara Hitler.

But to be thorough, I should consider that her full name might be Klara Hitler (née Pölzl), but the question asks for her name, and it's most commonly given as Klara Hitler.

So, final answer: Klara Hitler.

But I think I might be missing something. Maybe I should recall more details.

I remember that Klara Hitler was born in 1860 and died in 1907. She was married to Alois Hitler, and they had several children, but only Adolf and his siblings survived infancy.

But I'm not sure if this helps with the name. I think the name is indeed Klara Hitler.

But sometimes, in historical writing, people refer to her by her maiden name, Klara Pölzl, especially when discussing her early life or family background.

But in general, when referring to her in the context of Hitler's life, she is called Klara Hitler.

Therefore, the most appropriate answer is Klara Hitler.

But to cover all bases, perhaps it's best to give both names: Klara Pölzl (later Klara Hitler).

But the question asks for her name, and in the context of Hitler's mother, she is most commonly referred to as Klara Hitler.

So, I'll stick with Klara Hitler.

But I recall that in some biographies, she is referred to as Klara Pölzl.

Hmm, maybe the most complete answer is Klara Pölzl, as that is her full name, including her maiden name.

But in most contexts, especially when talking about her as Hitler's mother, she is called Klara Hitler.

I think both are correct, but Klara Hitler is more commonly used.

But to be precise, her full name was Klara Pölzl before marriage and Klara Hitler after marriage.

The question asks for her name, and it's common to refer to someone by their married name, especially if that's the name they were most commonly known by.

Therefore, the answer is Klara Hitler.

But I think it's also acceptable to say Klara Pölzl, especially if emphasizing her origins.

But since the question doesn't specify, and Klara Hitler is the more common reference, I'll go with that.

But to be thorough, perhaps the best answer is Klara Hitler (née Pölzl).

But in most historical writing, she is referred to as Klara Hitler.

Therefore, the answer is Klara Hitler.

But I'm not entirely sure. Maybe I should think differently.

Perhaps I can recall specific sources or books where her name is mentioned.

I remember reading that in "Mein Kampf," Hitler mentions his mother as Klara Hitler.

Yes, in his own writing, he refers to her as Klara Hitler.

Therefore, that is likely the correct name to use.

So, final answer: Klara Hitler.

But to be complete, her maiden name was Pölzl.

But the question asks for her name, and in the context of her being Hitler's mother, she is most commonly referred to as Klara Hitler.

Therefore, the answer is Klara Hitler.

But I think it's also correct to say Klara Pölzl, especially in a historical context where maiden names are important.

But since the question is about her name, and she was known as Klara Hitler during the time she was Hitler's mother, that seems to be the most appropriate answer.

But to cover all bases, perhaps it's best to say Klara Hitler (née Pölzl).

But in most cases, people refer to her as Klara Hitler.

Therefore, the answer is Klara Hitler.

But I think I might be overcomplicating this. The most common and likely correct answer is Klara Hitler.

So, I'll go with that.

</think>

*Summary:* Adolf Hitler's mother was Klara Hitler (née Pölzl). She is most commonly referred to as Klara Hitler in historical contexts, especially when discussing her role as Hitler's mother. However, her maiden name was Pölzl.

Thus, the answer is:

Adolf Hitler's mother was \boxed{Klara\ Hitler}.

Would be interesting to see a comparison with Qwen 32B. I found it a fantastic local model (ollama).

This thing is crazy fast.

Interesting that their niche seems to be small parameter models.