In-place refusal-direction edits of Qwen3.8-Flash-Next NVFP4. No tensor changes format — the edit is applied on the quantisation grid itself.
👋 Open to Work
Flare
lflare
AI & ML interests
None yet
Recent Activity
updated a model 5 days ago
lflare/Qwen3.8-Flash-Next-FLARE-Abliterated updated a model 9 days ago
lflare/ThinkingCap-Qwen3.6-27B-FP8 updated a model 9 days ago
lflare/Tess-4-27B-NVFP4A16Organizations
None yet
models 22
lflare/Qwen3.8-Flash-Next-FLARE-Abliterated
Image-Text-to-Text • Updated • 162 • 3
lflare/ThinkingCap-Qwen3.6-27B-FP8
Image-Text-to-Text • 28B • Updated • 36
lflare/Tess-4-27B-NVFP4A16
Image-Text-to-Text • 28B • Updated • 26
lflare/Tess-4-27B-FP8
Image-Text-to-Text • 28B • Updated • 36 • 1
lflare/Qwen3.8-Flash-Next-NVFP4-MXFP8-CSF-QAD-Abliterated
Image-Text-to-Text • 97B • Updated • 395 • 2
lflare/Qwen3.8-Flash-Next-NVFP4-Abliterated
Text Generation • 94B • Updated • 1.37k • 8
lflare/Qwen3.6-27B-uncensored-heretic-v2-mtp-NVFP4A16
Image-Text-to-Text • 28B • Updated • 82 • 2
lflare/Qwen3.6-27B-uncensored-heretic-v2-mtp-FP8
Image-Text-to-Text • 28B • Updated • 66 • 5
lflare/Qwen3.6-27B-uncensored-heretic-v2-mtp
Image-Text-to-Text • 28B • Updated • 39 • 4
lflare/Qwen3.6-27B-NVFP4A16
Image-Text-to-Text • 28B • Updated • 79 • 1
datasets 0
None public yet