alt Hacker NewsCurious 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.
Replies
UncleOxidant • today at 4:25 PM
That's a 2-bit quant of DS4 flash. You're probably better off running Qwen3.6-27B at Q8.
➕ show 5 replies
wolttam • today at 4:22 PM
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.
➕ show 1 reply
nunodonato • today at 4:13 PM
DS4-Flash is not only "significantly" smaller, it will also benefit from a lot more speed thanks to DSpark
➕ show 1 reply
> given they are pretty close in size
One thing that might not be obvious about about DSV4 is how much innovation the Deepseek team implemented in its architecture. When llama.cpp fully supports its lightning indexer, the full 1M context will only require about 6G of RAM. So even though they are similar in size, I believe Deepseek will be much more efficient in that regard.
> I wonder if Hy3 can compete there
Highly depends on how well Hy3 is resilient to quantization. DSV4 is useful even at 2-bit quants.