oobabooga

oobabooga's activity

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

New activity in unsloth/Qwen3.8-27B-NVFP4 about 2 months ago

Inferact/Qwen3.8-27B-NVFP4 is on vLLM's official documentation

10

#8 opened about 2 months ago by

pathosethoslogos

New activity in ubergarm/Qwen3.6-27B-GGUF 5 months ago

Great model for single GPU use cases.

🔥 4

16

#1 opened 5 months ago by

phakio

New activity in oobabooga/accurate-gguf-vram-calculator 7 months ago

issue: unable to calculate vram for Qwen3.5

1

#2 opened 7 months ago by

Daniel-H212

New activity in ByteDance-Seed/Seed-OSS-36B-Instruct about 1 year ago

Draft model for speculative decoding

➕ 6

#24 opened about 1 year ago by

oobabooga

New activity in unsloth/gpt-oss-20b-GGUF about 1 year ago

The jinja2 template contains a bug

👍 1

1

#18 opened about 1 year ago by

oobabooga

New activity in mradermacher/Qwen3-235B-A22B-i1-GGUF over 1 year ago

SOTA score

🔥 2

#1 opened over 1 year ago by

oobabooga

New activity in mradermacher/DeepSeek-V3-GGUF over 1 year ago

imatrix quants

29

#2 opened over 1 year ago by

oobabooga

New activity in oobabooga/CodeBooga-34B-v0.1 almost 3 years ago

Human eval results?

👍 1

4

#2 opened almost 3 years ago by

rombodawg

Merge 100% of the models instead of only parts

3

#1 opened almost 3 years ago by

rombodawg

New activity in OpenAssistant/oasst-sft-1-pythia-12b over 3 years ago

How can I run this?

12

#2 opened over 3 years ago by

Matan1905

New activity in PygmalionAI/pygmalion-6b over 3 years ago

Latest commits yield poor results with device_map='auto'

5

#8 opened over 3 years ago by

oobabooga

Latest commits yield poor results with device_map='auto'

5

#8 opened over 3 years ago by

oobabooga