Kir Belevich
deepsweet
AI & ML interests
Local inference and offline data.
Recent Activity
updated a model about 5 hours ago
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8 updated a model about 5 hours ago
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ4 published a model about 6 hours ago
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ4Organizations
None yet
Qwen3.6
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 10B • Updated • 2.17k • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16
Text Generation • 10B • Updated • 5.25k • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8
Text Generation • 10B • Updated • 110 -
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8-FP16
Text Generation • 10B • Updated • 772 • 1
YandexGPT
FLUX.2
GigaChat
-
deepsweet/GigaChat3.1-10B-A1.8B-MLX-oQ8
Text Generation • 3B • Updated • 532 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP4
Text Generation • 11B • Updated • 450 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP8
Text Generation • 11B • Updated • 211 -
deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
Text Generation • 11B • Updated • 98
Qwen3.5
-
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP8
Text Generation • 35B • Updated • 196 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4-FP16
Text Generation • 6B • Updated • 457 • 2 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4
Text Generation • 6B • Updated • 967 • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP4-FP16
Text Generation • 35B • Updated • 400
Z-Image
FLUX.2
Qwen3.6
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 10B • Updated • 2.17k • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16
Text Generation • 10B • Updated • 5.25k • 3 -
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8
Text Generation • 10B • Updated • 110 -
deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8-FP16
Text Generation • 10B • Updated • 772 • 1
GigaChat
-
deepsweet/GigaChat3.1-10B-A1.8B-MLX-oQ8
Text Generation • 3B • Updated • 532 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP4
Text Generation • 11B • Updated • 450 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP8
Text Generation • 11B • Updated • 211 -
deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
Text Generation • 11B • Updated • 98
YandexGPT
Qwen3.5
-
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP8
Text Generation • 35B • Updated • 196 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4-FP16
Text Generation • 6B • Updated • 457 • 2 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4
Text Generation • 6B • Updated • 967 • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP4-FP16
Text Generation • 35B • Updated • 400