News for hackers. Stuff that matters.
Re:Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update by armcat on Saturday November 14, 2026 @04:21AM (#50495446)
Great work as always Dan! I've used Qwen3.8 quite a bit and it's very verbose - its propensity for tool calling is insane and it uses 2x as many tokens as GLM-5.2 (which itself uses huge amount of tokens). I'm wondering if you have any plans to incorporate Bottlecap AI Qwen3.8 [1] checkpoints? They have done post-training where they significantly improve the token efficiency.

[1] https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-27B-G...

Re:Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update by danielhanchen on Saturday November 14, 2026 @04:56AM (#50495640)
Oh yes I think I saw bottecap's work - very interesting!

For Qwen3.8-Flash-Next (I know not 27B haha), we actually cut reasoning by up to 50% esp for the small quants - we found quantizing models naively coincidentally also made them more verbose, as it would "correct" itself during the reasoning process. We managed to make the extra token usage of lower bit quants now only be +5% vs BF16 vs +50% extra from other quants.

27B should have similar benefits, but it's less as it's a smaller model!

Re:Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update by armcat on Saturday November 14, 2026 @05:27AM (#50495816)
Interesting, thanks for the info! Incidentally we've been testing nvfp4 weights vs vanilla 16-bit, GLM-5.3 in this case, and found that the vanilla 16 bit ones use 10x more tokens, but the output is more stable and better quality (less Chinese characters appearing, better coding solutions). So to me it's all just alchemy at this point.
Re:Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update by danielhanchen on Saturday November 14, 2026 @06:57AM (#50496307)
Oh yes interesting!