Kir Belevich
deepsweet
AI & ML interests
Local inference and offline data.
Recent Activity
new activity about 2 hours ago
deepsweet/Qwen3.6-27B-MLX-oQ8-FP16:Is there a benchmark comparison between DFLASH and native MTP? updated a collection about 12 hours ago
Qwen3.6-35B-A3B updated a collection about 12 hours ago
Qwen3.6-35B-A3BOrganizations
None yet
Z-Image
GigaChat
-
deepsweet/GigaChat3.1-10B-A1.8B-MLX-oQ8
Text Generation • 3B • Updated • 356 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP4
Text Generation • 11B • Updated • 439 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP8
Text Generation • 11B • Updated • 173 -
deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
Text Generation • 11B • Updated • 68
Qwen3.5
-
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP8
Text Generation • 35B • Updated • 147 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4-FP16
Text Generation • 6B • Updated • 614 • 2 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4
Text Generation • 6B • Updated • 214 • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP4-FP16
Text Generation • 35B • Updated • 438
Qwen3.6-35B-A3B
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 10B • Updated • 4.85k • 5 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ6
Text Generation • 8B • Updated • 38 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ5
Text Generation • 7B • Updated • 2.02k • 1 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ4
Text Generation • 6B • Updated • 4.1k • 3
FLUX.2
YandexGPT
Qwen3.6-27B
Qwen3.6-35B-A3B
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 10B • Updated • 4.85k • 5 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ6
Text Generation • 8B • Updated • 38 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ5
Text Generation • 7B • Updated • 2.02k • 1 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ4
Text Generation • 6B • Updated • 4.1k • 3
Z-Image
FLUX.2
GigaChat
-
deepsweet/GigaChat3.1-10B-A1.8B-MLX-oQ8
Text Generation • 3B • Updated • 356 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP4
Text Generation • 11B • Updated • 439 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP8
Text Generation • 11B • Updated • 173 -
deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
Text Generation • 11B • Updated • 68
YandexGPT
Qwen3.5
-
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP8
Text Generation • 35B • Updated • 147 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4-FP16
Text Generation • 6B • Updated • 614 • 2 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4
Text Generation • 6B • Updated • 214 • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP4-FP16
Text Generation • 35B • Updated • 438