[flagged]
Mistral Medium 3.5
161–170 of 248 posts
Re: Mistral Medium 3.5
#162For it's size, that's really good! Though I bet it being a dense model probably helps a lot, if it was MoE at that size, I bet the benchmark performance would go quite a bit down (which consequently would also mean that I'd at least be able to run it with decent tokens/second, with the bunch of Nvidia L4 cards available to me, which presently are only okay with MoE models).
It's cool that they added comparisons to their own Mistral Small 4 119B A7B, which kind of shows that! They could have also included comparisons to something like Qwen Coder Next 80B A3B (or maybe the newer Qwen 3.6 35B A3B, or the 27B dense one), maybe DeepSeek V4 Flash 284B A13B, or the older GPT-OSS 120B A5B to illustrate that difference and where their model sits even better, it would probably give a more positive picture than just comparing themselves against a bunch of bigger models!
Come to think of it, alongside throwing some money at DeepSeek not just Anthropic, I probably should get a Mistral subscription as well sometime, to see how they perform on various tasks - cause they seem pretty cost effective and it's nice to support at least some EU orgs: https://mistral.ai/pricing
Re: Mistral Medium 3.5
#163Re: Mistral Medium 3.5
#164Earlier quoted context omitted.
> Cloud hardware can run the original model. Quantization will reduce quality. New models are often being released in quantized format to begin with. This is true of both Kimi and the new DeepSeek V4 series. There is no "original model", the model is generated using Quantization Aware Training (QAT).
> There is no "original model", the model is generated using Quantization Aware Training (QAT). The original model is the model used for the benchmarks People will say "You can run it locally!" then show the benchmarks of the original model, but what they really mean is that you can run a heavily quantized adaptation of the model which has difference performance characteristics.
That remark was specific to newer models like Kimi 2.x and DeepSeek V4 series, and this is clearly stated in my comment.
As for other models, we quantize them because we are generally constrained by the model's total footprint in bytes, and running a larger model that's been quantized to fit in the same footprint as a smaller one improves performance compared to a smaller original, generally up to Q4 or so, with even tighter quantizations (up to Q2) being usable for some uses such as general Q&A chat.
Re: Mistral Medium 3.5
#165I'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…
Eh. Those results would be noteworthy if it was a a MoE. A 120B dense? Firmly in meh territory.
Why do you care?
Re: Mistral Medium 3.5
#166It's funny that 128B is now considered Medium. I remember back in the day when 355 M parameters was considered medium with GPT-2.
And GPT-2 1.5B was considered too dangerous to release. They were perhaps right.
considered that by OpenAI for marketing purposes that is
But yes, perhaps it would have been better for all of us if they haven't.
Re: Mistral Medium 3.5
#167Earlier quoted context omitted.
I agree there is a difference but does that translate to anything? It's not the same operations used to write code, and it's kind of useless. I wouldn't waste my power bill ensuring a model I was releasing was good at it.
> It's not the same operations used to write code Is it not? It's html and javascript. And not even attempting to draw details that other models do. When I try other html / js prompts it also lacks behind china models from over half a year ago. I mean worse then GLM 4.7.
I've only tried it via the web so far and it's working great for my usual test prompts. Looks like it was trained on some pretty recent data.
Re: Mistral Medium 3.5
#168Earlier quoted context omitted.
Where? All I see is Boris saying "we are unable to issue compensation for degraded service or technical errors that result in incorrect billing routing".
Keep this in mind next time you hear someone talking about "removing the human in the loop". Anthropic apparently won't take responsibility for issues their own systems handling billing cause. You think they'll take responsibility in your system when a bug in their models can be demonstrated as the cause?
> Anthropic apparently won't take responsibility for issues their own systems handling billing cause.
I think with every org, especially the big ones, trying to dodge responsibility (setting the intent of "customer support" to be annoying them enough for them to buzz off), the only recourse people have is to give them enough bad press where they wake up and do the refund, it's less than a rounding error for them.
I think Anthropic is hardly unique in that position and being able to chat with a human with any sort of power to actually make things right is becoming more and more rare. If any human eyes saw that, the correct thing to do would probably be passing the message up the chain like "Hey, this will have really bad optics if we don't do the right thing. Can you take like 5 minutes and hit the refund button while I draft up a nice message about it?"
Re: Mistral Medium 3.5
#169Earlier quoted context omitted.
Where are the competitive models from Singapore, Japan, Taiwan, Korea, Russia, Canada, India, the UK? From anywhere that isn't China or the US? There are none. Mistral Small 4 is pareto-competitive in its pricing bracket at $0.15/$0.60, at worst it's second to Gemma 4 26B A4B. The above countries have never had a model that is even close to being so. This particular Mistral Medium looks to be uncompetitive at that pr…
What does Pareto competitive mean here? Look at the pricing of the V4-flash model: https://api-docs.deepseek.com/quick_start/pricing
80 percent as good for 20 percent the cost.
Re: Mistral Medium 3.5
#170Earlier quoted context omitted.
I didn't know about HERMES.md ... (??) - found information here for others who are curious https://github.com/anthropics/claude-code/issues/53262
This github thread is incredible, thanks for sharing. This link should be its own HN topic.