🦀 dancing crab

Damien

el4

·

https://codeberg.org/el_4

AI & ML interests

I do anything really | #quantwizard | ETH: 0xDEE7fa8C421BD038D32e4441ea1aDe72fE973706

Recent Activity

liked a model about 2 hours ago

chaoliangUNSW/Jev-Style-0.8B-Decision-v3-GGUF

liked a model about 7 hours ago

nomic-ai/nomic-embed-text-v2-moe-GGUF

repliedto CompactAI's post 6 days ago

@Compactbot is going live in about a week (could be shorter or longer) Its going to reply to this post (when it finds it) but will not be live until a later post says so. https://huggingface.co/spaces/Glint-Research/blog

View all activity

Organizations

None yet

New activity in zai-org/GLM-5.3-Flash 16 days ago

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

#40 opened 23 days ago by

New activity in ornith-ai/Ornith-1.5-35B-A3B 22 days ago

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

#31 opened 29 days ago by

New activity in el4/Xenon-26B-A4B 23 days ago

good writer

#1 opened 23 days ago by

New activity in el4/Ornith-1.5-35B-A3B-ONYX-GGUF 24 days ago

LET'S GO!!

#1 opened 24 days ago by

New activity in el4/Qwen3.8-27B-ONYX-GGUF 24 days ago

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

#2 opened about 1 month ago by

New activity in el4/GRM-3.2-Sky-ONYX-GGUF 25 days ago

BF16

#3 opened 25 days ago by

New activity in Qwen/Qwen3.8-27B about 1 month ago

Request: DOI

#139 opened about 1 month ago by

New activity in el4/Qwen3.8-27B-ONYX-GGUF about 1 month ago

Just Curious...

#1 opened about 1 month ago by

New activity in unsloth/Qwen3.8-27B-GGUF about 1 month ago

Q4_K_M gets wrong output using kobold.cpp

#55 opened about 1 month ago by

New activity in el4/GRM-3.2-Sky-ONYX-GGUF about 1 month ago

Amazing model

#2 opened about 2 months ago by

New activity in el4/SIQ-1-35B-ONYX-GGUF about 1 month ago

These ONYX Quants are sick!

#1 opened about 1 month ago by

New activity in OrionLLM/GRM-3.2-Sky about 1 month ago

Benchmark validity?

#1 opened about 2 months ago by

New activity in meta-models/Muse-Glimmer-30B about 2 months ago

WE REALLY NEED 9B-12B OR 35B A3B MOE🔥🔥🔥

#15 opened about 2 months ago by

THANKS FOR BLOCKING MY COUNTRY FROM DOWNLOADING THESE MODELS

#29 opened about 2 months ago by

New activity in openai/gpt-oss-20b about 2 months ago

Still the undisputed best model for 16gb consumer cards, when can we expect a refresh / new model?

#265 opened 3 months ago by

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

Oops

#1 opened about 2 months ago by

New activity in Manusagents/GPT-5.5-Gemini-3.1-Pro-Grok-4-Claude-Fable-5-Mythos-5-Qwen-3.7-Max-and-more-Distillation-Dataset about 2 months ago

multiple (potential) contaminations

#3 opened 2 months ago by

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

Benchmark results

#3 opened about 2 months ago by

Performance issues on Quality quantization.

#2 opened about 2 months ago by

When loading the compact gguf with LLama.cpp I am getting an error

#1 opened about 2 months ago by