Qwen 3.5 9b better at false smoke and workbench
Sam
stamsam
AI & ML interests
None yet
Recent Activity
new activity about 17 hours ago
stamsam/Qwen3.6-28B-REAP-oQ4:Does MLX support smaller quantizations? published a model 1 day ago
stamsam/Gemma-4-21B-REAP-JANG3M-MLX updated a model 1 day ago
stamsam/Gemma-4-21B-REAP-JANG3M-MLXOrganizations
models 15
stamsam/Gemma-4-21B-REAP-JANG3M-MLX
Text Generation • 3B • Updated • 73
stamsam/Qwen3.6-28B-REAP-oQ4
Text Generation • 5B • Updated • 123
stamsam/Gemma_4_Gem_e4b-NF4-Textonly
Text Generation • 8B • Updated • 4
stamsam/Gemma_4_Gem_e4b_multimodal-NF4
Image-Text-to-Text • 6B • Updated • 3
stamsam/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-MLX-oQ4-MTP
Text Generation • 35B • Updated • 4.19k • 4
stamsam/Qwenjamin_Franklin_4bit
Text Generation • 1B • Updated • 28
stamsam/Qwenjamin_Franklin_V2_4bit
Text Generation • 1B • Updated • 25
stamsam/Qwenjamin_Franklin_V2
Text Generation • 9B • Updated • 14
stamsam/Qwenjamin_Franklin
Text Generation • 9B • Updated • 5
stamsam/Gemma-E2B-Chimera-Multimodal-v4-MLX-4bit
Image-Text-to-Text • 1B • Updated • 130
datasets 0
None public yet