Vontra/Qwen3.8-27B-NVFP4
Updated
AI & ML interests
Exploring local AI and sharing MLX work with the community.
Recent Activity
ashxhart
published a
model about 16 hours ago
ashxhart
updated 7
models about 16 hours ago
Vontra/Qwen3.8-27B-oQ2
Image-Text-to-Text • 3B • Updated • 1
Vontra/Qwen3.8-27B-oQ8
Image-Text-to-Text • 8B • Updated
Vontra/Qwen3.8-27B-oQ6
Image-Text-to-Text • 6B • Updated
Vontra/Qwen3.8-27B-oQ4
Image-Text-to-Text • 5B • Updated
Vontra/Qwen3.8-27B-MLX-8bit
Image-Text-to-Text • 8B • Updated
Vontra/Qwen3.8-27B-MLX-6bit
Image-Text-to-Text • 6B • Updated
Vontra/Qwen3.8-27B-MLX-4bit
Image-Text-to-Text • 5B • Updated
ashxhart
published 7
models about 16 hours ago
Vontra/Qwen3.8-27B-oQ2
Image-Text-to-Text • 3B • Updated • 1
Vontra/Qwen3.8-27B-oQ8
Image-Text-to-Text • 8B • Updated
Vontra/Qwen3.8-27B-oQ6
Image-Text-to-Text • 6B • Updated
Vontra/Qwen3.8-27B-oQ4
Image-Text-to-Text • 5B • Updated
Vontra/Qwen3.8-27B-MLX-8bit
Image-Text-to-Text • 8B • Updated
Vontra/Qwen3.8-27B-MLX-6bit
Image-Text-to-Text • 6B • Updated
Vontra/Qwen3.8-27B-MLX-4bit
Image-Text-to-Text • 5B • Updated
ashxhart
updated a
model 1 day ago
ashxhart
published a
model 1 day ago
Does DeepSeek-V4-Flash-0731-MXFP4-MLX work with oMLX 0.5.7
9
#1 opened 8 days ago
by 
Polygons
ashxhart
updated a
model 3 days ago
ashxhart
published a
model 3 days ago