Qwen 3.5 9b better at false smoke and workbench
🏝️ On Vacation
Sam
stamsam
AI & ML interests
None yet
Organizations
models 22
stamsam/maple-preview-gguf
Text Generation • 20B • Updated • 1.41k • 15
stamsam/Instella-Prometheus-GGUF
Text Generation • 16B • Updated • 108
stamsam/Instella-Prometheus
Text Generation • 16B • Updated • 296
stamsam/Gemma_4_Gem_e4b_multimodal-NF4
Image-Text-to-Text • 6B • Updated • 24
stamsam/MedusaGemma-E4B_MLX_4Bit
Text Generation • 8B • Updated • 32
stamsam/MedusaGemma-E4B
Text Generation • 8B • Updated • 21 • 1
stamsam/FrankenGemma4_MLX_4Bit
Text Generation • 8B • Updated • 18 • 1
stamsam/FrankenGemma4
Text Generation • 1B • Updated • 32 • 6
stamsam/Gemma-4-12B-a4B-MoE
12B • Updated • 515 • 5
stamsam/Qwen3.6-28B-REAP-mixedbit-tuned-mlx
Text Generation • 28B • Updated • 30 • 2
datasets 0
None public yet