← Back to context

Comment by pinyen_cheng

10 hours ago

I think the future should be efficient quantization which can make model with the same level as Qwen 3.8 27b now accessible from our laptop.

9 comments

pinyen_cheng

Reply
throwa356262  4 hours ago

The future is already here :)

These 3bit ISTA quants of qwen are supposed to be 95% as accurate as the full model and runs moothly on laptops:

https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF

There are multiple independent tests of this on YouTube.

  • latentsea  4 hours ago

    They aren't "Just as accurate". What you see with these quants is the providers only ever show performance on already saturated benchmarks. You'll see labs put out 1-bit quants Deepseek v4.1 claiming only 1% degradation because they're only showing the benchmarks which tell that story. Then you look at the performance on those same benchmarks for significantly weaker models like Qwen3.8-27B even and it's virtually the same because that benchmark is saturated.

    I like these quants as much as the next guy when they're all I can run but I have both R9700 with 32GB VRAM and a 5060 Ti with only 16GB VRAM and so I run both Q6 Unlsoth quants and ISTA IQ3_XXS quants and yeah there is an absolute world of difference in realworld performance.

    IMHO I think it's pretty scummy behavior from the quant providers to frame these quants this way. Just be honest about where the degradation is really occurring on the non-saturated benchmarks.

    • starfallg  1 hour ago

      This is a really good point that goes the other way as well. Some use cases are great for smaller and cheaper models, but it's not obviously when that's the case so I can bank the savings.

    • bestham  3 hours ago

      All I know is that Strata and these models are the most I have ever gotten out of my machine. I get 70 t/s on a standard gaming rig 9070 XT / 5900X / 64 GB DDR4 @3400.

  • postepowanieadm  4 hours ago

    I don't know, it hallucinates quite badly - confuses js with python.

    • user_7832  2 hours ago

      Apparently the ud-q4_k_xl version of qwen 3.8 27b is quite better than the q3 and not much larger. At least per r/localllama. (I'm also trying to find a good local model).

Moto7451  9 hours ago

This is mostly a memory bandwidth issue. Qwen 3.8 27b and the related Bonsai 2 27B run on my M5 Max laptop with 36GB of ram. It’s a little slow due to my specific model having lower memory bandwidth than higher end models with more ram and cores. MoE models perform better here and expert streaming engines can allow larger than memory models to run.

  • nout  9 hours ago

    Multiple teams and efforts are now making Qwen 3.8 27b work much faster on Mac and CUDA and the inference speed is doubling almost every week. There's now ongoing competition about who will make it work faster with exactly the same byte output at https://mlx.fast . TensorFold is the project to follow.