Hy3

50 points | by andai an hour ago

19 comments

  • Catloafdev 21 minutes ago

    Curious how people feel about this compared to DS4 Flash, given they are pretty close in size. Also curious how well it holds up to heavy quantization.

    DS4 Flash can currently run reasonably well on systems with ~96gb+ RAM, I wonder if Hy3 can compete there.

    Edit: not as close in size as I initially thought: 299B vs 165B

      wolttam 11 minutes ago

      Hy3 lacks the DSv4 architecture's KV Cache efficiency.

      Whereas I can run DSv4 Flash on a pair of DGX Sparks and have enough memory left over for 3M tokens of KV cache, with Hy3 (quantized to FP4), there is only room for ~130K tokens of KV cache.

      UncleOxidant 8 minutes ago

      That's a 2-bit quant of DS4 flash. You're probably better off running Qwen3.6-27B at Q8.

        sosodev 3 minutes ago

        I suspect it would depend on the task. DS4-flash does, as previously mentioned, handle quantization very well. Even at 2-bit it's still very coherent.

      nunodonato 20 minutes ago

      DS4-Flash is not only "significantly" smaller, it will also benefit from a lot more speed thanks to DSpark

        Catloafdev 7 minutes ago

        Oh apparently I misread the size, I thought it was much closer at first.

        299B for Hy3 vs 165B for Flash - not quite comparable

  • minraws 30 minutes ago

    I tried out the model it's pretty great, better than gpt5.4 perhaps, atleast close enough to sonnet 5 in performance that I didn't notice much of a gap.

    Not really at gpt 5.5 tier though, and probably below glm 5.2...

    But most of all it just works for me for most things I tried and it's exceedingly cheap so there is no reason not to use it, if you need a foss model.

      cbg0 a minute ago

      Hy3 DeepSWE - 28%

      GPT5.4 xhigh DeepSWE - 52%

      A lot of contaminated benchmarks in the blog post about Hy3, needs real testing though I have a distinct feeling it's benchmaxxed like a lot of Chinese models.

      theplumber a minute ago

      I think you’ve got the models wrong…gpt-5.4? I doubt there is any open source mode matching it. Maybe in a year

  • nshotton 27 minutes ago

    This model is shockingly small for how capable it is. its a little bit bigger than deepseekV4 flash but around as capable if not more on some benchmarks than V4 pro, i wouldnt be surprised if this becomes a popular local model.

      andai 21 minutes ago

      I've been wondering about that. GLM-5.2 is also half the size of DeepSeek V4 Pro. (But costs roughly twice as much.)

      I looked into DeepSeek's architecture a little bit and the main focus was how can we save as much money as possible. They did a lot of cost cutting with the attention mechanisms. This allowed them to offer an insanely cheap price even on massive contexts, but seems to have come at the cost of performance?

      At least, that's my guess, when I see smaller models costing more and outperforming, I think, "they must have denser attention?"

      nunodonato 26 minutes ago

      hardly, its still quite big unless by "local" you mean people that spend many thousands on rigs :)

        nshotton 22 minutes ago

        Yeah i shouldve been more clear, a model of this size could run on 2 dgx sparks so out of the range of a lot of the typical consumer sure, but I think there is definitely a market for that size

      IshKebab 20 minutes ago

      > Hy3 has 295B parameters in total. To serve it on 8 GPUs, we recommend using H20-3e or other GPUs with larger memory capacity.

      I would.

  • throwaway2027 14 minutes ago

    Quite interesting to see them and Meta and others release before OpenAI supposedly is to release GPT 5.6 today, would it be better to release it before or after? Calm before the storm type of thing?

  • james2doyle 17 minutes ago

    Been using this and GLM 5.2 back and forth. I like the speed of Hy3. Also seems very happy to follow instructions. Still haven’t found any open models that follow instructions as good as Mimo v2 pro though

  • handzhiev 26 minutes ago

    It's a very good model for this size and price. I tried it with a couple of small tasks - just an year ago this would be the level of the leading models.

  • smir 33 minutes ago

    Visited the link thinking it's for hy lang, found it's another llm from tencent, anyway it's nice read

  • nunodonato 27 minutes ago

    Very impressive model for its size