Viewing profile — coder543

I think glancing at a random snapshot from today misses all the context. Nemotron 3 is far more significant than you're giving it credit for. At this point, Nemotron 3 is really an…

Yes, the article uses AI-assisted text, so if that offends you, no need to accuse: you can just stop reading. I have a good amount of background knowledge on all of this, and I've …

A year and a half behind Seedance 2.0? That is a bold claim that needs evidence. According to one user preference leaderboard, MiniMax H3 is already ahead of Seedance 2.0 based on …

The weights were just released a few minutes ago: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731

But if you compare to Anthropic's models? The cost difference is huge. Anthropic is clearly concerned that people are realizing they are expensive, since the Opus 5 blog post dedic…

This article seems premature to post. Right now, the price is arbitrarily set by a single provider. Why wouldn't Moonshot collect extra revenue during this exclusivity period when …

At this point, I would not recommend ignoring Parakeet TDT 0.6b v2/v3 (english-only versus multilingual). Those models have been out for a year, give or take, and they are both acc…

It’s not FUD. It is my actual, lived experience. FUD is false, which this is not. I use both vLLM and llama-server. vLLM is very painful, even with the Spark community docker image…

Unsloth Studio is also very low effort, and a lot better than LM Studio in my opinion. (Performance, compatibility with Gemma 4, actually open source, etc.)

Compared to a dynamic quant like Unsloth's UD-Q4_K_XL, which keeps some important parameters in higher precision, a basic NVFP4 quant seems to do a lot more damage to the model unl…

> The systems but old but I’m seeing 11tks 27b, 15tks 35b MoE If that's accurate, then you must be doing something wrong/weird. On a single RTX 3090, I'm seeing substantially highe…

> For a MBP I have 48 GB of RAM M5 Pro. It runs at about 12-14 t/s at Q4 Are you running with MTP enabled? I have seen some people on M5 hardware report 20+ t/s on Qwen3.6-27B usin…

5.5 Pro is $30 in / $180 out: https://developers.openai.com/api/docs/pricing I think you meant 5.5. I agree it is probably the same size model. It's probably exactly built on top o…

EDIT: It's just not even worth arguing this point, so deleting my original, much longer comment. Abstract taxonomies can claim that Taalas is CIM, but this entirely and utterly mis…

CIM does not bake the weights into silicon. The level of optimization that you can do down to the last transistor when the weights are fixed is on an entirely different level than …

Yes, I’m focused on the topic at hand that the person I replied to was also talking about. The person I replied to was acting as if Taalas was ancient history. I was pointing out i…

> It's odd to me that I haven't heard anything about this approach since. It has only been four months since they unveiled their first prototype. I don't understand your confusion.…

Taalas' first chip is for a Llama 3.1 8B quant, not a 3.1B parameter model, to clarify.

Yeah... one of the relevant issues: https://github.com/openai/codex/issues/11940#issuecomment-45... You would think they would support their own GPT-OSS model, but, not really anym…

Well, the reason is simple: over the past several months, it has become very difficult to use Codex with non-OpenAI models. They removed the old edit tool that didn't require OpenA…

> I have come to consider Gemma 4 31b the best model I can self-host I'm confused. Your own results show that Gemma 4 26B A4B and Qwen3.6-27B did better in these tests? I really li…