alt Hacker NewsThere are Qwen3.5 27B quants in the range of 4 bits per weight, which fits into 16G of VRAM. The quality is comparable to Sonnet 4.0 from summer 2025. Inference speed is very good with ik_llama.cpp, and still decent with mainline llama.cpp.
Replies
zozbot234 • yesterday at 8:04 AM
With MoE models, if the complete weights for inactive experts almost fit in RAM you can set up mmap use and they will be streamed from disk when needed. There's obviously a slowdown but it is quite gradual, and even less relevant if you use fast storage.
➕ show 1 reply
teaearlgraycold • yesterday at 7:41 AM
Qwen3.5 35B A3B is much much faster and fits if you get a 3 bit version. How fast are you getting 27B to run?
On my M3 Air w/ 24GB of memory 27B is 2 tok/s but 35B A3B is 14-22 tok/s which is actually usable.
➕ show 2 replies
Can someone explain how a 27B model (quantized no less) ever be comparable to a model like Sonnet 4.0 which is likely in the mid to high hundreds of billions of parameters?
Is it really just more training data? I doubt it’s architecture improvements, or at the very least, I imagine any architecture improvements are marginal.