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

A few words on DS4

antirez.com

Post reply on HN
Print view View original

121–130 of 197 posts

Re: A few words on DS4

#121

Post by zozbot234 »

ljosifov wrote: post #119

Love this, even if can't use it atm (not got the h/w - only 96gb on M2 Max). I get it the general comp/public will find it unusable or worse. Reminds me of how home computers were - mere toys - before they became personal computers (PC). On my h/w the only passable combo for me atm is pi agent + llama.cpp + nemotron cascade-2 model: to 1M context, hybrid arch doesn't crash & burn 1/N^2 with context depths of 10K-50K-…

It should work with 96GB, especially on a limited context. But the M2 Max is a bit slower, yes.

Re: A few words on DS4

#122

Post by smcleod »

gcr wrote: post #46

DwarfStar4 is a small LLM inference runtime that can run DeepSeek 4. The blog post implies that it currently requires 96GB of VRAM. For others who are lacking context :-)

That's the flash version not the full model and only at Q2-3~ so while impressive it's still quite different from the full model.

Re: A few words on DS4

#123

Post by Hamuko »

pavlov wrote: post #98
oezi wrote: post #69

Earlier quoted context omitted.

Or a car from Citroen

Technically DS is an independent sibling of Citroën within Stellantis, a sprawling car conglomerate that owns a dog’s dinner of car brands in Europe and USA.

If we want to get really technical, “DS4” is a model from Citroën and they later spun out the DS lineup into its separate brand, with the “Citroën DS4” becoming “DS 4”, “DS” being the make and “4” being the model.

Re: A few words on DS4

#125

Post by zozbot234 »

petercooper wrote: post #120

I've been using the Q4 version on my Mac Studio over my local network and it's been good. Indeed, I had the first ever experience where I was playing with it alongside my various other agents and forgot it was a local model as it was doing such a good job. I do wonder, though, if another agent is really needed. I've been driving it with Pi (Claude Code's system prompt is far too heavy given the prefill speeds) and it…

DS4 is an inference engine, not a harness. It provides an inference API server and you point your coding harness to it.

Re: A few words on DS4

#126

Post by antirez »

petercooper wrote: post #120

I've been using the Q4 version on my Mac Studio over my local network and it's been good. Indeed, I had the first ever experience where I was playing with it alongside my various other agents and forgot it was a local model as it was doing such a good job. I do wonder, though, if another agent is really needed. I've been driving it with Pi (Claude Code's system prompt is far too heavy given the prefill speeds) and it…

There is no need for another agent, functionally. But if you follow the idea of DS4 itself: the API agents use forces to do odd things, like translating the DSML stanzas to JSON, with all the canonicalization / KV cache checkpointing problems resulting from that. Is it really the case? What about also providing a sane alternative? Also I'm not sure why people don't try to write more stuff in that area in C/Go/Rust to have more control / speed / less dependences.

Also there is a lot more to imagine, TUI side. The problem is that most projects all copy what they already saw. For instance I just did this in 20 minutes: https://x.com/antirez/status/2055190821373116619 Now that code is cheap, ideas have more value. Are we sure that today it is still the case to think in terms: "Is another XYZ needed"? It could be the case that only just to explore new ideas, it is worth it. I I don't like the Javascript / Node ecosystem for my code, so if I have to explore a new TUI or agent workflow, if I do it with the tools I'm more happy to use, the result, the iterations, are different.

Re: A few words on DS4

#127

Post by antirez »

zozbot234 wrote: post #125
petercooper wrote: post #120

I've been using the Q4 version on my Mac Studio over my local network and it's been good. Indeed, I had the first ever experience where I was playing with it alongside my various other agents and forgot it was a local model as it was doing such a good job. I do wonder, though, if another agent is really needed. I've been driving it with Pi (Claude Code's system prompt is far too heavy given the prefill speeds) and it…

DS4 is an inference engine, not a harness. It provides an inference API server and you point your coding harness to it.

You misunderstood the OP. I hinted, in my blog, at my interest to also putting an agent harness inside.

Re: A few words on DS4

#128

Post by zozbot234 »

karel-3d wrote: post #124

Oh a local DeepSeek? Nice > Starting from MacBooks with 96GB of RAM. ... oh. And I thought I bought a lot with 48 GB.

96GB is what the author claims will work in a foolproof way for easy production use. But nothing stops you from trying to run it on 48GB, it ought to gracefully fall back on accessing model layers from the disk.

Re: A few words on DS4

#129

Post by zozbot234 »

antirez wrote: post #126
petercooper wrote: post #120

I've been using the Q4 version on my Mac Studio over my local network and it's been good. Indeed, I had the first ever experience where I was playing with it alongside my various other agents and forgot it was a local model as it was doing such a good job. I do wonder, though, if another agent is really needed. I've been driving it with Pi (Claude Code's system prompt is far too heavy given the prefill speeds) and it…

There is no need for another agent, functionally. But if you follow the idea of DS4 itself: the API agents use forces to do odd things, like translating the DSML stanzas to JSON, with all the canonicalization / KV cache checkpointing problems resulting from that. Is it really the case? What about also providing a sane alternative? Also I'm not sure why people don't try to write more stuff in that area in C/Go/Rust to…

> ...I'm not sure why people don't try to write more stuff in C to have more control / speed / less dependences.

Codex CLI is written in Rust, which should give comparable raw performance to C/C++. Of course you can care about the "less dependencies" point but this is somewhat less of a concern on a properly maintained project like Codex. That's not so much "wild, out of control" third-party dependencies and closer to the old ideal of proper software componentry.

> Also there is a lot more to imagine, TUI side. The problem is that most projects all copy what they already saw. For instance I just did this in 20 minutes.

This mockup is really nice and the sidebar display gives you a natural way to expose running multiple thinking flows in parallel, at least if you keep them from stepping on each other's toes with code edits (keep them all in read-only "plan" mode or working on completely separate directories/files). That's not so helpful on a 128GB MacBook where a single agentic flow brings you to thermal/power limits already, but it suddenly becomes useful on other hardware (DGX Spark, Strix Halo, lower-RAM machines with SSD offload, multiple nodes with pipeline parallelism) where you have more compute than you could use for single-stream decode.

Re: A few words on DS4

#130

Post by pavlov »

Hamuko wrote: post #123
pavlov wrote: post #98

Earlier quoted context omitted.

Technically DS is an independent sibling of Citroën within Stellantis, a sprawling car conglomerate that owns a dog’s dinner of car brands in Europe and USA.

If we want to get really technical, “DS4” is a model from Citroën and they later spun out the DS lineup into its separate brand, with the “Citroën DS4” becoming “DS 4”, “DS” being the make and “4” being the model.

And even more pedantically, DS has recently adopted a new naming scheme where the former DS 4 is now written as DS N°4, pronounced "number 4"...

Their stated inspiration for this SEO bomb is Chanel perfumes.

Post reply on HN