Sebastian

sjug's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 1 month ago

sjug/DeepSeek-V3.2-MLX-4bit

Text Generation • 672B • Updated Dec 4, 2025 • 432

published a model about 1 month ago

sjug/DeepSeek-V3.2-MLX-4bit

Text Generation • 672B • Updated Dec 4, 2025 • 432

updated a model 4 months ago

sjug/gpt-oss-120b-mlx-mxfp4

Text Generation • 117B • Updated Aug 29, 2025 • 29

published a model 4 months ago

sjug/gpt-oss-120b-mlx-mxfp4

Text Generation • 117B • Updated Aug 29, 2025 • 29

updated a model 5 months ago

sjug/Qwen3-235B-A22B-Instruct-2507-MLX-9bit

Text Generation • 235B • Updated Aug 27, 2025 • 17

published a model 5 months ago

sjug/Qwen3-235B-A22B-Instruct-2507-MLX-9bit

Text Generation • 235B • Updated Aug 27, 2025 • 17

updated a model 5 months ago

sjug/GLM-4.5-MLX-9bit

Text Generation • 353B • Updated Aug 25, 2025 • 9

published a model 5 months ago

sjug/GLM-4.5-MLX-9bit

Text Generation • 353B • Updated Aug 25, 2025 • 9

liked a model 6 months ago

mlx-community/GLM-4.5-4bit

Text Generation • 353B • Updated Jul 28, 2025 • 160 • 16

updated a model 6 months ago

sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit

Text Generation • 235B • Updated Jul 26, 2025 • 16

published a model 6 months ago

sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit

Text Generation • 235B • Updated Jul 26, 2025 • 16

liked a model 6 months ago

Qwen/Qwen3-235B-A22B-Instruct-2507

Text Generation • 235B • Updated Sep 17, 2025 • 89.3k • • 742

New activity in mlx-community/medgemma-27b-text-it-8bit 7 months ago

mlx-community/medgemma-27b-text-it-8bit does not stop generating output

2

#1 opened 8 months ago by

sjug

upvoted a collection 7 months ago

Qwen3

Collection

84 items • Updated 11 days ago • 1.56k

liked a model 7 months ago

Qwen/Qwen3-235B-A22B-MLX-8bit

Text Generation • 62B • Updated Jul 7, 2025 • 83 • 9

New activity in mlx-community/medgemma-27b-text-it-bf16 8 months ago

mlx-community/medgemma-27b-text-it-bf16 is entirely broken on mlx-lm

👍 1

8

#1 opened 8 months ago by

sjug

liked a model 9 months ago

Qwen/Qwen3-235B-A22B

Text Generation • 235B • Updated Jul 26, 2025 • 253k • • 1.07k

updated a model 9 months ago

sjug/Mistral-Large-Instruct-2411-8bit

Text Generation • 38B • Updated Apr 23, 2025 • 39

published a model 9 months ago

sjug/Mistral-Large-Instruct-2411-8bit

Text Generation • 38B • Updated Apr 23, 2025 • 39

updated a model 9 months ago

sjug/Llama-3_3-Nemotron-Super-49B-v1-8bit

Text Generation • 16B • Updated Apr 23, 2025 • 9