David

xdavxd's activity

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

upvoted a collection 15 days ago

MeditronFO

Collection

The first fully open medical specialist LLM, outperforms Medgemma on open-ended clinical evaluation • 9 items • Updated Jun 25 • 4

New activity in RedHatAI/gemma-4-12B-it-NVFP4 16 days ago

Recipe ideas

2

#2 opened 24 days ago by

xdavxd

updated a model 19 days ago

xdavxd/gemma-4-26B-A4B-it-qat-heretic-ega-NVFP4

Image-Text-to-Text • 26B • Updated 19 days ago • 77

published a model 19 days ago

xdavxd/gemma-4-26B-A4B-it-qat-heretic-ega-NVFP4

Image-Text-to-Text • 26B • Updated 19 days ago • 77

updated a model 19 days ago

xdavxd/gemma-4-26B-A4B-it-qat-heretic-ega

Image-Text-to-Text • 26B • Updated 19 days ago • 86

published a model 21 days ago

xdavxd/gemma-4-26B-A4B-it-qat-heretic-ega

Image-Text-to-Text • 26B • Updated 19 days ago • 86

updated 2 models 23 days ago

xdavxd/gemma-4-12B-it-heretic-v2-NVFP4

Image-Text-to-Text • 12B • Updated 23 days ago • 243

xdavxd/gemma-4-26B-A4B-it-heretic-NVFP4

Image-Text-to-Text • 26B • Updated 23 days ago • 58

New activity in RedHatAI/gemma-4-26B-A4B-it-NVFP4 24 days ago

Better generation defaults?

#9 opened 2 months ago by

xdavxd

New activity in xdavxd/gemma-4-12B-it-heretic-v2-NVFP4 24 days ago

Updated on 2026-09-02 to fix audio transcription and bake FP8 KV scales

#2 opened 24 days ago by

xdavxd

updated a model 24 days ago

xdavxd/gemma-4-12B-it-heretic-NVFP4

Image-Text-to-Text • 12B • Updated 23 days ago • 148

New activity in TrevorJS/gemma-4-12B-it-uncensored 25 days ago

Audio transcription degrades under NVFP4 quantization (BF16 is fine)

6

#1 opened about 1 month ago by

xdavxd

liked a model 27 days ago

basically-ai/Pebble-10M-Chat

Text Generation • 11.1M • Updated 26 days ago • 1.55k • 13

updated a collection about 1 month ago

Heretic NVFP4

Collection

NVFP4 quantized versions of de-censored models for use with vLLM. • 5 items • Updated about 1 month ago

published a model about 1 month ago

xdavxd/gemma-4-12B-it-heretic-v2-NVFP4

Image-Text-to-Text • 12B • Updated 23 days ago • 243

updated a collection about 1 month ago

Heretic NVFP4

Collection

NVFP4 quantized versions of de-censored models for use with vLLM. • 5 items • Updated about 1 month ago

updated a model about 1 month ago

xdavxd/gemma-4-26B-A4B-it-heretic-v2-NVFP4

Image-Text-to-Text • 14B • Updated about 1 month ago • 359 • 2

upvoted an article about 1 month ago

view article

Article

Granite 4.2 LLMs: How They're Built

• 

ibm-granite

•

Aug 25

• 124

New activity in mradermacher/model_requests about 1 month ago

https://huggingface.co/swiss-ai/Apertus-v1.5-8B

7

#2763 opened about 2 months ago by

xdavxd

New activity in mradermacher/model_requests about 2 months ago

https://huggingface.co/swiss-ai/Apertus-v1.5-70B

2

#2764 opened about 2 months ago by

xdavxd