Mistral releases Devstral2 and Mistral Vibe CLI • Hacker News Board

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#161

Post by gunalx » Tue, Dec 09, 2025, 8:00 PM UTC

fastball wrote: post #46

pzmarzly wrote: post #15

10x cheaper price per token than Claude, am I reading it right? As long as it doesn't mean 10x worse performance, that's a good selling point.

Is it? The actual SOTA are not amazing at coding, so at least for me there is absolutely no reason to optimize on price at the moment. If I am going to use an LLM for coding it makes little sense to settle for a worse coder.

I dunno. Even pretty weak models can be decently performant, and 9/10 the performance for 1/10 the price means 10x the output, and for a lot of stuff that quality difference dosent really matter. Considering even sota models are trash, slightly worse dosent really make that much difference.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#162

Post by clusterhacks » Tue, Dec 09, 2025, 8:02 PM UTC

monster_truck wrote: post #136

princehonest wrote: post #79

Let's say you had a hardware budget of $5,000. What machine would you buy or build to run Devstral Small 2? The HuggingFace page claims it can run on a Mac with 32 GB of memory or an RTX 4090. What kind of tokens per second would you get on each? What about DGX Spark? What about RTX 5090 or Pro series? What about external GPUs on Oculink with a mini PC?

I'd throw a 7900xtx in an AM4 rig with 128gb of ddr4 (which is what I've been using for the past two years) Fuck nvidia

You know, I haven't even been thinking about those AMD gpus for local llms and it is clearly a blind spot for me.

How is it? I'd guess a bunch of the MoE models actually run well?

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#163

Post by syntaxing » Tue, Dec 09, 2025, 8:05 PM UTC

Extremely happy with this release, the previous Devstral was great but training it for open hands crippled the usefulness. Having their own CLI dev tool will hopefully be better

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#164

Post by maelito » Tue, Dec 09, 2025, 8:06 PM UTC

Finally, we can use a european model to replace claude code.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#165

Post by eavan0 » Tue, Dec 09, 2025, 8:11 PM UTC

I'm glad it's not another LLM CLI that uses React. Vibe-cli seems to be built with https://github.com/textualize/textual/

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#166

Post by macNchz » Tue, Dec 09, 2025, 8:15 PM UTC

johanvts wrote: post #89

embedding-shape wrote: post #63

Earlier quoted context omitted.

I did, although a long time ago, so maybe I need to try it again. But it still seems to be stuck in a chat-like interface instead of something tailored to software development. Think IDE but better.

It has a new “watch files” mode where you can work interactively. You just code normally but can send commands to the llm via a special string. Its a great way if interacting with LLMs, if only they where much faster.

If you're interested in much faster LLM coding, GLM 4.6 on Cerebras is pretty mind blowing. It's not quite as smart as the latest Claude and Gemini, but it generates code so fast it's kind of comical if you're used to the other models. Good with Aider since you can keep it on a tighter leash than with a fully agentic tool.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#167

Post by simonw » Tue, Dec 09, 2025, 8:23 PM UTC

The system prompt and tool prompts for their open source (Apache 2 licensed) Python+Textual+Pydantic CLI tool are fun to read:

core/prompts/cli.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c...

core/prompts/compact.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c...

.../prompts/bash.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c...

.../prompts/grep.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c...

.../prompts/read_file.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c...

.../prompts/write_file.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c...

.../prompts/search_replace.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c...

.../prompts/todo.md https://github.com/mistralai/mistral-vibe/blob/v1.0.4/vibe/c...

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#168

Post by fastball » Tue, Dec 09, 2025, 8:30 PM UTC

whimblepop wrote: post #158

fastball wrote: post #113

Earlier quoted context omitted.

Where are you getting this compendium of commonly-accepted definitions? Looking up open-source in the dictionary does include definitions that would allow for commercial restrictions, depending on how you define "free" (a matter that is most certainly up for debate).

"Open-source" isn't a term that emerged organically from conversations between people. It is a term that was very deliberately coined for a specific purpose, defined into existence by an authority. It's a term of art, and its exact definition is available here: https://opensource.org/osd The term "open-source" exists for the purposes of a particular movement. If you are "for" the misuse and abuse of the term, you not…

yeahhhhhhh, that's not how this works.

Unless this authority has some ownership over the term and can prevent its misuse (e.g. with lawsuits or similar), it is not actually the authority of the term, and people will continue to use it how they see fit.

Indeed, I am not part of a movement (nor would I want to be) which focuses more on what words are used rather than what actions are taken.

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#169

Post by lubujackson » Tue, Dec 09, 2025, 8:30 PM UTC

cpursley wrote: post #35

simonw wrote: post #33

llm install llm-mistral llm mistral refresh llm -m mistral/devstral-2512 "Generate an SVG of a pelican riding a bicycle" https://tools.simonwillison.net/svg-render#%3Csvg%20xmlns%3D... Pretty good for a 123B model! (That said I'm not 100% certain I guessed the correct model ID, I asked Mistral here: https://x.com/simonw/status/1998435424847675429 )

Skipped the bicycle entirely and upgraded to a sweet motorcycle :)

The Batman motorcycle!

Re: Mistral releases Devstral2 and Mistral Vibe CLI

#170

Post by fastball » Tue, Dec 09, 2025, 8:33 PM UTC

gunalx wrote: post #161

fastball wrote: post #46

Earlier quoted context omitted.

Is it? The actual SOTA are not amazing at coding, so at least for me there is absolutely no reason to optimize on price at the moment. If I am going to use an LLM for coding it makes little sense to settle for a worse coder.

I dunno. Even pretty weak models can be decently performant, and 9/10 the performance for 1/10 the price means 10x the output, and for a lot of stuff that quality difference dosent really matter. Considering even sota models are trash, slightly worse dosent really make that much difference.

> SOTA models are "trash"

> this model is worse (but cheaper)

> use it to output 10x the amount of trashier trash

You've lost me.