Kir Belevich
deepsweet
AI & ML interests
Local inference and offline data.
Recent Activity
new activity about 10 hours ago
unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit:There is no benchmark for mlx models new activity 1 day ago
deepsweet/Qwen3.6-27B-DFlash-FP16:Openclaw compatibility problem new activity 1 day ago
z-lab/Qwen3.6-27B-DFlash:I used it on Omlx,but it showed thinking as content.Organizations
None yet
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 10B • Updated • 4.01k • 4 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16
Text Generation • 10B • Updated • 7.15k • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8
Text Generation • 10B • Updated • 361 -
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8-FP16
Text Generation • 10B • Updated • 1.47k • 1
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 10B • Updated • 4.01k • 4 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16
Text Generation • 10B • Updated • 7.15k • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8
Text Generation • 10B • Updated • 361 -
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8-FP16
Text Generation • 10B • Updated • 1.47k • 1
models 36
deepsweet/Qwen3.6-27B-DFlash-FP16
Text Generation • Updated • 243 • 2
deepsweet/Qwen3.6-35B-A3B-DFlash-FP16
Text Generation • Updated • 566 • 1
deepsweet/Qwen3.6-27B-MLX-oQ4-FP16
Text Generation • 4B • Updated • 1.24k
deepsweet/Qwen3.6-27B-MLX-oQ5-FP16
Text Generation • 5B • Updated • 873
deepsweet/Qwen3.6-27B-MLX-oQ8-FP16
Text Generation • 8B • Updated • 2.32k • 2
deepsweet/Qwen3.6-35B-A3B-MLX-oQ5-FP16
Text Generation • 7B • Updated • 2.52k
deepsweet/Qwen3.6-35B-A3B-MLX-oQ5
Text Generation • 7B • Updated • 1.3k • 1
deepsweet/Qwen3.6-35B-A3B-MLX-oQ4
Text Generation • 6B • Updated • 2.9k • 2
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16
Text Generation • 10B • Updated • 7.15k • 3
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 10B • Updated • 4.01k • 4