Damien

el4's activity

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

New activity in burner22/numbat about 5 hours ago

Random Chinese symbols sometimes appearing in output

🤯🤗 2

4

#45 opened about 6 hours ago by

kimi-chan

New activity in burner22/numbat about 13 hours ago

Beware of this model, Hugging Face automatically reports 6.8T parameters, while the uploader claims approximately 14T.

9

#6 opened 2 days ago by

Metris

New activity in InternScience/Sage-A1.5 8 days ago

Cheers to the best qwen 35b moe finetune ive used so far! 🍺

🚀 1

#7 opened 8 days ago by

el4

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 13 days ago

Q2/Q3 what doas that mean?

19

#10 opened 20 days ago by

kalle07

New activity in stepfun-ai/Step-5-Preview 18 days ago

Tool call feedback

#3 opened 18 days ago by

el4

New activity in hugging-science/QUESTION_YALL 28 days ago

YOO WHAT?

60

#1 opened about 1 month ago by

Bc-AI

New activity in hugging-science/ripp 29 days ago

WAKE UP

11

#5 opened 29 days ago by

GGUFGuy

New activity in el4/Whittle-Qwen-3.8-35B-A3B-ONYX-GGUF 29 days ago

Parent Updated!

3

#1 opened about 1 month ago by

alifarajpahlou

New activity in hugging-science/ripp about 1 month ago

Agentic Coding Harness I forked + opensourcing all of my GPU poor research

🚀👍 1

#4 opened about 1 month ago by

el4

Message board idea

👍 6

7

#3 opened about 1 month ago by

el4

New activity in deepgrove/maple-preview about 1 month ago

5.31 GB where?

1

#10 opened about 1 month ago by

MackTuesday

New activity in whittleOrg/Whittle-Qwen-3.8-35B-A3B about 1 month ago

woah 🔥

🔥 2

#1 opened about 1 month ago by

el4

New activity in zai-org/GLM-5.3-Flash about 2 months ago

Folks with smaller VRAM but enough RAM - Token per second almost doubled for Q3 (unsloth)

6

#40 opened 2 months ago by

nizoai

New activity in ornith-ai/Ornith-1.5-35B-A3B 2 months ago

I Benchmarked on RTX 5090: 271 tok/s generation, 673 tok/s at 8 concurrent, 32 KB/token KV cache

2

#31 opened 2 months ago by

laxmimerit

New activity in el4/Xenon-26B-A4B 2 months ago

good writer

🤗 2

4

#1 opened 2 months ago by

Naphula

New activity in el4/Ornith-1.5-35B-A3B-ONYX-GGUF 2 months ago

LET'S GO!!

🔥 1

3

#1 opened 2 months ago by

NeatOnTheRocks

New activity in el4/Qwen3.8-27B-ONYX-GGUF 2 months ago

YES!!! Thrilled to see; will test mini vs. UD-IQ3_XXS

🔥 3

7

#2 opened 3 months ago by

NeatOnTheRocks

New activity in el4/GRM-3.2-Sky-ONYX-GGUF 2 months ago

BF16

1

#3 opened 2 months ago by

saipangon

New activity in Qwen/Qwen3.8-27B 3 months ago

Request: DOI

🔥 1

1

#139 opened 3 months ago by

Bimzypermanent

New activity in el4/Qwen3.8-27B-ONYX-GGUF 3 months ago

Just Curious...

3

#1 opened 3 months ago by

Czavodsky