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

5 comments

• aliljet 17 minutes ago
  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 ..
• nout 1 hour ago
  How does it compare to the 3.8-27B versions from TensorFold? I.e. does it make sense to run unsloth via TensorFold engine?
• ilaksh 1 hour ago
  How do the smallest quants of this compare to Bonsai 2?
  [-]
  • DiabloD3 1 hour ago
    Bonsai 2 doesn't work at all, Unsloth's smallest... also doesn't work, but is still better.

    Bonsai's technology would be better suited for 100s of B models.
• jan_Sate 2 hours ago
  Awesome! I wonder how it does at Q5+ compared with v3.0
• namjh 1 hour ago
  [dead]