Brian Dellabetta

bdellabe's activity

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

New activity in RedHatAI/gemma-4-31B-it-FP8-block 4 days ago

Could you also provide FP8-block version of the gemma-4-31B-it drafted model?

2

#5 opened 8 days ago by

RayHuang1991

New activity in RedHatAI/gemma-4-31B-it-NVFP4 4 days ago

Turboquant and mtp?

1

#8 opened 9 days ago by

tasticleeze

liked a model 13 days ago

sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4

12B • Updated 11 days ago • 637 • 2

New activity in RedHatAI/gemma-4-26B-A4B-it-FP8-Dynamic 14 days ago

Update chat_template.jinja

1

#4 opened 14 days ago by

bdellabe

New activity in RedHatAI/gemma-4-26B-A4B-it-NVFP4 14 days ago

Update chat_template.jinja

#5 opened 14 days ago by

bdellabe

updated 2 models 14 days ago

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

33B • Updated 14 days ago • 240k • 19

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

Image-Text-to-Text • 31B • Updated 14 days ago • 245k • 27

New activity in RedHatAI/gemma-4-31B-it-NVFP4 14 days ago

Request: Update Chat Template to match Base Model

1

#6 opened 15 days ago by

yasu-oh

updated a model 14 days ago

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

Image-Text-to-Text • 20B • Updated 14 days ago • 194k • 41

updated 2 models 18 days ago

RedHatAI/Kimi-K2.6-FP8-BLOCK

1T • Updated 18 days ago • 1.66k • 4

RedHatAI/Kimi-K2.6-NVFP4

Updated 18 days ago • 17.6k • 12

published a model 18 days ago

RedHatAI/Kimi-K2.6-NVFP4

Updated 18 days ago • 17.6k • 12

published 2 models 19 days ago

bdellabe/upload-large-folder

Updated 19 days ago

RedHatAI/Kimi-K2.6-FP8-BLOCK

1T • Updated 18 days ago • 1.66k • 4

New activity in moonshotai/Kimi-K2.6 20 days ago

fix: add missing use_deterministic_attn parameter to MoonViT3dEncoder

5

#22 opened 25 days ago by

ace-coreweave

New activity in RedHatAI/gemma-4-31B-it-NVFP4 about 1 month ago

Error KeyError: 'layers.0.experts.0.down_proj.input_global_scale' when running on vllm

1

#5 opened about 1 month ago by

pachePizza

Running Gemma 4 Truthfully at 128K on One RTX 5090

3

#4 opened about 1 month ago by

Mosai-Sys

New activity in RedHatAI/gemma-4-31B-it-FP8-block about 1 month ago

Problem on Nvidia DGX Spark

1

#4 opened about 1 month ago by

akalongman

Inference is slow with A100

1

#3 opened about 1 month ago by

weisunding

Update README.md

1

#2 opened about 1 month ago by

bullerwins