Qwen3.8 27B: 4-bit quantization matches full model, 1-bit collapses

I would be very interested in a similar benchmark for *KV cache* quantizations.

I use Qwen3.8 27B Q4_K_M for coding sometimes and therefore need a relatively long context. I settled on q8_0 because it is the only way to fit the model + 100k tokens into 24GB VRAM, but still wonder what am I loosing in quality, and what other options are there.

I also heard that KV cache quantization matters more with longer contexts. It may be interesting to benchmark this too: what the quality looks like on different combinations of model quantization × KV cache quantization × context size.

This confirms a theory I have to explain the minimal loss in quality when using lower quants (I use IQ3_XXS with an 8-bit KV cache) and the XHIGH (default) thinking level.

It's well-known that while quantization affects the sampling probability distribution (given the same context, which next token is the most probable), Qwen 3.8 27b seems to offset that by just thinking more and as a result eventually finishing the task (benchmark or otherwise).

So as long as the thinking (albeit longer) is sound, this leads to the same success rate (as shown in the article) but potentially at the cost of more tokens and hence more time.

I think it'll be further useful to chart each quantization's used tokens as well, in addition to the success rate.

Thanks for doing and sharing the research!

There's a real hole here at Q3. A critical breakpoint here is sub 16-GB cards, which covers the 5080, 5070 Ti, 5060ti, and several other cards from this generation and the last. It would be instructive to see where the quality knee is.

hmm, assuming that this article is part written by claude and part human-written, can anyone help me find a rule of thumb for "how to know if the article is worth reading"?

Because on the one hand, the prose and the presentation is painful (narrating irrelevant points, nonlinear X-axes, ambiguous chart labels, etc etc),

But on the other hand, the result that I'm assuming the author means to communicate ("on these evals, generation quality seems fairly good") sounds worthwhile to share?

Because I really struggle with this question at the moment. Am I allowed to draw an adverse inference that "if the writeup presents irrelevant text side by side with the data, then this may be a sign that the author does not understand the task that they are attempting to write up"?

Measuring quality e2e definitely makes sense.

But I think there is a bit more to this:

> Measuring token prediction differences (KL-divergence, top-1 predictions) is easy, but it does not tell us whether the model gets worse at solving tasks.

A common issue is that it's rarely mentioned on which dataset KL-divergence is computed. It seems the most common dataset is wikitext - maybe because of tradition, to make numbers more comparable? It's not measuring how well the model follows bf16 on agentic tasks.

I've been trying to check KLD recently for some quants of Qwen 3.8 27B, and the numbers are dramatically different, depending on which dataset you use. KLD computed on agentic traces is much higher, and top-1 % is way lower than if you compute it on chats or wiki text.

You look at a published number, and see "oh, nice, top1 is 99% - quant is different just in 1 token out of 100", but chances are it's computed on wiki, and on agentic / coding it can be 10 tokens out of 100.

Common intuition is that on agentic tasks errors compound, and that's why it degrades more than metrics show - but maybe the metrics themselves are also wrong, too optimistic.

Still investigating it though :)

I always wonder is it safe to run one of these models on a personal pc, or do you guys recommend something like docker, sorry a bit new to all of this.

If you want to do a 1-bit model you have to QAT at pre-training with way more data than chinchilla to compensate for the cliffs (like 50x). Quantization on an existing pre-trained model will almost always collapse at 1-bit