Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update

Retro_Dev 74 points 10 comments November 14, 2026
unsloth.ai · View on Hacker News

Discussion Highlights (6 comments)

jan_Sate

Awesome! I wonder how it does at Q5+ compared with v3.0

ilaksh

How do the smallest quants of this compare to Bonsai 2?

nout

How does it compare to the 3.8-27B versions from TensorFold? I.e. does it make sense to run unsloth via TensorFold engine?

aliljet

There are so many of us with weak GPUs and these updates are massive wins. Still waiting for the 2080 moment where this 27B param model and a reasonable kv cache can exist and function at slow, but overnight-burning speeds ..

hacker_88

Figuring out local llms , but it did built me single page html . On 12 GB VRAM and 16 GB ram windows .

quaddoggy

Just installed Qwen 3.8 Splash tonight (doesn’t appear on linked page). Super impressed. Easily averaging 45 tps, even with thinking on. Totally acceptable. Running M4 Mac mini, 48GB, LM Studio.

Semantic search powered by Rivestack pgvector
12,728 stories · 120,417 chunks indexed