Kir Belevich
deepsweet
AI & ML interests
MLX
Recent Activity
updated a dataset 24 days ago
deepsweet/mdn new activity about 1 month ago
deepsweet/Qwen3.6-27B-DFlash-FP16:How can I convert z-lab/Qwen3.8-27B-DFlash2 to fp16? updated a model about 1 month ago
deepsweet/Qwen3.8-27B-DFlash2-FP16Organizations
None yet
Qwen3.6-35B-A3B
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 35B • Updated • 157 • 8 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ6
Text Generation • 35B • Updated • 42 • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ5
Text Generation • 35B • Updated • 49 • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ4
Text Generation • 35B • Updated • 65 • 5
FLUX.2
YandexGPT
Qwen3.6-27B
Z-Image
GigaChat
-
deepsweet/GigaChat3.1-10B-A1.8B-MLX-oQ8
Text Generation • 11B • Updated • 33 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP4
Text Generation • 11B • Updated • 90 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP8
Text Generation • 11B • Updated • 50 -
deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
Text Generation • 11B • Updated • 24
Qwen3.5
-
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP8
Text Generation • 35B • Updated • 36 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4-FP16
Text Generation • 35B • Updated • 43 • 2 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4
Text Generation • 35B • Updated • 33 • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP4-FP16
Text Generation • 35B • Updated • 39
Ornith-1.0-35B
Qwen3.6-27B
Qwen3.6-35B-A3B
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 35B • Updated • 157 • 8 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ6
Text Generation • 35B • Updated • 42 • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ5
Text Generation • 35B • Updated • 49 • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ4
Text Generation • 35B • Updated • 65 • 5
Z-Image
FLUX.2
GigaChat
-
deepsweet/GigaChat3.1-10B-A1.8B-MLX-oQ8
Text Generation • 11B • Updated • 33 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP4
Text Generation • 11B • Updated • 90 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP8
Text Generation • 11B • Updated • 50 -
deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
Text Generation • 11B • Updated • 24
YandexGPT
Qwen3.5
-
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP8
Text Generation • 35B • Updated • 36 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4-FP16
Text Generation • 35B • Updated • 43 • 2 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4
Text Generation • 35B • Updated • 33 • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP4-FP16
Text Generation • 35B • Updated • 39