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

Mistral Medium 3.5

mistral.ai

Post reply on HN
Print view View original

61–70 of 248 posts

Re: Mistral Medium 3.5

#61

Post by Mashimo »

Compared to all other hosted LLMs that I have tested, Mistral seems to be the only one with rather strict CSP headers. When you ask them to create a website with some javascript library it will not preview, even though le chat offers canvas mode.

Sometimes when a new release comes around from any provider I just want to test it a bit on the web. without paying and using an agent harness.

Why are they like this ;_;

Edit: Christ on a bike it's bad at drawing SVGs https://chat.mistral.ai/chat/23214adb-5530-4af9-bb47-90f5219...

Re: Mistral Medium 3.5

#62

Post by gregsadetsky »

simjnd wrote: post #52

I'm not sure what people are on in the comments. It doesn't beat the other models, but it sure competes despite its size. GLM 5.1 is an excellent model, but even at Q4 you're looking at ~400GB. Kimi K2.5 is really good too, and at Q4 quantization you're looking at almost ~600GB. This model? You can run it at Q4 with 70GB of VRAM. This is approaching consumer level territory (you can get a Mac Studio with 128GB of RAM…

I didn't know about HERMES.md ... (??) - found information here for others who are curious https://github.com/anthropics/claude-code/issues/53262

Re: Mistral Medium 3.5

#64

Post by Mashimo »

simonw wrote: post #47
simonw wrote: post #40

I can't figure out if this is available in the official Mistral API or not. Their model listing API returns this: { "id": "mistral-medium-2508", "object": "model", "created": 1777479384, "owned_by": "mistralai", "capabilities": { "completion_chat": true, "function_calling": true, "reasoning": false, "completion_fim": false, "fine_tuning": true, "vision": true, "ocr": false, "classification": false, "moderation": fals…

Some poking around in the source code for https://github.com/mistralai/mistral-vibe got me to this: curl https://api.mistral.ai/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $(llm keys get mistral)" \ -d '{ "model": "mistral-medium-3.5", "messages": [ {"role": "user", "content": "Generate an SVG of a pelican riding a bicycle"} ] }' Which did work: https://gist.github.com/simonw…

I also did some SVG tests, it's really bad.

https://chat.mistral.ai/chat/897fbe7d-b1ae-4109-9b29-f3ccc4f...

Re: Mistral Medium 3.5

#65

Post by seb_lz »

I'm using mistral-medium-2508 for some text transformation operations. It's giving me better results than mistral-large for my use cases. Looking forward to testing this new model, although I'm not sure if it's really meant at replacing the previous medium model since it's a lot more expensive and presented more as a coding / agentic model (mistral-medium-2508 was priced $0.4/$2 per 1M tokens, mistral-medium-3.5 is $1,5/$7.5).

Re: Mistral Medium 3.5

#66

Post by spwa4 »

Marciplan wrote: post #26
spwa4 wrote: post #6

TLDR: Mistral Medium 3.5, text-only, 128B dense model, 256k context window, modified MIT license. Model is ~140G ... https://huggingface.co/mistralai/Mistral-Medium-3.5-128B They more or less claim this exceeds Claude Sonnet 3.5 on most things, but is worse than Sonnet 3.6, and exceeds all other open models. Oh and they have a cloud service that will code your apps "in the cloud". But, yeah, at this point, so does my…

You mean Sonnet 4.5 and 4.6 riight

right

Re: Mistral Medium 3.5

#67

Post by YetAnotherNick »

simjnd wrote: post #52

I'm not sure what people are on in the comments. It doesn't beat the other models, but it sure competes despite its size. GLM 5.1 is an excellent model, but even at Q4 you're looking at ~400GB. Kimi K2.5 is really good too, and at Q4 quantization you're looking at almost ~600GB. This model? You can run it at Q4 with 70GB of VRAM. This is approaching consumer level territory (you can get a Mac Studio with 128GB of RAM…

It has similar SWE bench score to qwen 3.6 27b[1]. No one is comparing it to frontier.

[1]: There is no other common benchmark in the blog.

Re: Mistral Medium 3.5

#68

Post by syntaxing »

This is a very interesting strategy that might pay off. This model is a very good option for enterprise self host. I would argue a lot of companies are VRAM constrained rather than compute constrained. You could fit 4-5 running instances on one H100 cluster where you can only fit 1-2 Kimi K2 or GLM5.

Re: Mistral Medium 3.5

#69

Post by spijdar »

Mashimo wrote: post #64
simonw wrote: post #47

Earlier quoted context omitted.

Some poking around in the source code for https://github.com/mistralai/mistral-vibe got me to this: curl https://api.mistral.ai/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $(llm keys get mistral)" \ -d '{ "model": "mistral-medium-3.5", "messages": [ {"role": "user", "content": "Generate an SVG of a pelican riding a bicycle"} ] }' Which did work: https://gist.github.com/simonw…

I also did some SVG tests, it's really bad. https://chat.mistral.ai/chat/897fbe7d-b1ae-4109-9b29-f3ccc4f...

Wow. I get that "how well can it make SVGs" isn't the (or a) gold standard for how useful a model is or isn't, but the fact the Gemma 4 26B A4B I'm running locally can blow it out of the water doesn't give me high confidence for the model. Maybe an unfair comparison, but...

Re: Mistral Medium 3.5

#70

Post by deaux »

NitpickLawyer wrote: post #14
tpurves wrote: post #12

Earlier quoted context omitted.

If it's not US and it's within a few percent of SOTA that might be good enough for a lot of people (eg Europeans)

Gemma has been better for us at EU languages than mistral (for comparable sized models) :/ so ... dunno. What mistral does well and others are lagging behind is deploying on prem with their engineers and know-how, offering tuned models for your tasks and finetuning on your own data. (I expect google to start offering this next)

It's sad that despite their strength in this for onprem, they're so behind on this in the cloud. No publicly available cloud SFT at all. Meanwhile Google has been offering that for years - though remains to be seen if they will for Gemini 3 when GA.

And on top of it a range of providers like Fireworks and so on that offer it for Chinese models. This seems such an obvious thing for Mistral to offer.

Post reply on HN