Modelpublic

mlx-community/Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp

sourceHugging Faceotherupdated 11d agoView on Hugging Face

6likes2.7kdownloads

3 commits on main

c7d915c11d ago

Full model card: quantization layout, calibration, 128 GB requirements, measured 262k-context performance; add LICENSE

timteh673

6792db112d ago

Upload Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp via oMLX

timteh673

44cd4fd12d ago

initial commit

timteh673