Brian Dellabetta

bdellabe's activity

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

updated a model about 7 hours ago

RedHatAI/gemma-4-31B-it-FP8-Dynamic

33B • Updated about 6 hours ago

published a model about 7 hours ago

RedHatAI/gemma-4-31B-it-FP8-Dynamic

33B • Updated about 6 hours ago

New activity in nm-testing/MiniMax-M2.5-W4A16 2 days ago

oneshot vs model_free_ptq? which one has better recovery?

1

#1 opened 3 days ago by

traphix

updated 2 models 3 days ago

nm-testing/MiniMax-M2.5-W4A16

Text Generation • 230B • Updated 3 days ago • 349

RedHatAI/gemma-4-31B-it-NVFP4

Image-Text-to-Text • 20B • Updated 2 days ago • 4.72k • 10

published a model 3 days ago

RedHatAI/gemma-4-31B-it-NVFP4

Image-Text-to-Text • 20B • Updated 2 days ago • 4.72k • 10

updated a model 3 days ago

RedHatAI/gemma-4-31B-it-FP8-block

Image-Text-to-Text • 31B • Updated 2 days ago • 1.97k • 5

published a model 3 days ago

RedHatAI/gemma-4-31B-it-FP8-block

Image-Text-to-Text • 31B • Updated 2 days ago • 1.97k • 5

published a model 5 days ago

nm-testing/MiniMax-M2.5-W4A16

Text Generation • 230B • Updated 3 days ago • 349

updated a model 12 days ago

nm-testing/Qwen3.5-35B-A3B-awq-w4a16

35B • Updated 12 days ago • 20

published a model 12 days ago

nm-testing/Qwen3.5-35B-A3B-awq-w4a16

35B • Updated 12 days ago • 20

updated a model 18 days ago

RedHatAI/DeepSeek-V3.2-NVFP4-FP8-BLOCK

384B • Updated 18 days ago • 629

updated a model 19 days ago

RedHatAI/DeepSeek-R1-NVFP4-FP8-BLOCK

397B • Updated 19 days ago • 56

published a model 19 days ago

RedHatAI/DeepSeek-V3.2-NVFP4-FP8-BLOCK

384B • Updated 18 days ago • 629

updated a model 19 days ago

bdellabe/DeepSeek-V3.2-NVFP4-FP8-BLOCK

384B • Updated 19 days ago • 307

published a model 19 days ago

bdellabe/DeepSeek-V3.2-NVFP4-FP8-BLOCK

384B • Updated 19 days ago • 307

New activity in inference-optimization/Qwen3-Coder-Next.w4a16 24 days ago

Question about weight_observer？

2

#1 opened 25 days ago by

traphix

updated a model about 2 months ago

bdellabe/DeepSeek-V2-Lite-FP8-BLOCK

16B • Updated Feb 17 • 10

published a model about 2 months ago

bdellabe/DeepSeek-V2-Lite-FP8-BLOCK

16B • Updated Feb 17 • 10

New activity in Qwen/Qwen3-Coder-Next about 2 months ago

AWQ quantization

👀 1

9

#1 opened 2 months ago by

dr-e