Kir Belevich
deepsweet
AI & ML interests
Local inference and offline data.
Recent Activity
published a model 9 minutes ago
deepsweet/Qwen3.6-27B-MLX-oQ5-FP16 upvoted an article 20 minutes ago
Why Maybe We're Measuring LLM Compression Wrong new activity 44 minutes ago
deepsweet/Qwen3.6-35B-A3B-MLX-VLM-oQ8-FP16:non FP16 : M3+ version of VLMOrganizations
None yet
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16
Text Generation • 10B • Updated • 4.86k • 2 -
deepsweet/Qwen3.6-35B-A3B-MLX-VLM-oQ8-FP16
Text Generation • 10B • Updated • 608 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 10B • Updated • 1.76k • 2 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ5-FP16
Text Generation • 7B • Updated • 1.68k
-
deepsweet/GigaChat3.1-10B-A1.8B-MLX-oQ8
Text Generation • 3B • Updated • 516 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP4
Text Generation • 11B • Updated • 512 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP8
Text Generation • 11B • Updated • 230 -
deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
Text Generation • 11B • Updated • 102
-
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP8
Text Generation • 35B • Updated • 196 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4-FP16
Text Generation • 6B • Updated • 408 • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4
Text Generation • 6B • Updated • 1.06k • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP4-FP16
Text Generation • 35B • Updated • 395
-
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16
Text Generation • 10B • Updated • 4.86k • 2 -
deepsweet/Qwen3.6-35B-A3B-MLX-VLM-oQ8-FP16
Text Generation • 10B • Updated • 608 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ8
Text Generation • 10B • Updated • 1.76k • 2 -
deepsweet/Qwen3.6-35B-A3B-MLX-oQ5-FP16
Text Generation • 7B • Updated • 1.68k
-
deepsweet/GigaChat3.1-10B-A1.8B-MLX-oQ8
Text Generation • 3B • Updated • 516 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP4
Text Generation • 11B • Updated • 512 -
deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP8
Text Generation • 11B • Updated • 230 -
deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
Text Generation • 11B • Updated • 102
-
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP8
Text Generation • 35B • Updated • 196 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4-FP16
Text Generation • 6B • Updated • 408 • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4
Text Generation • 6B • Updated • 1.06k • 1 -
deepsweet/Qwen3.5-35B-A3B-MLX-MXFP4-FP16
Text Generation • 35B • Updated • 395