John Leimgruber III's picture

John Leimgruber III

ubergarm

·

https://www.paypal.com/donate/?hosted_button_id=HU59345BZVSUA

AI & ML interests

Open LLMs and Astrophotography image processing.

Recent Activity

published a model 6 minutes ago

ubergarm/Qwen3-Coder-480B-A35B-Instruct-GGUF

updated a model about 4 hours ago

ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF

new activity about 5 hours ago

ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Compatibility with Nexesenex/croco.cpp ???

View all activity

Organizations

None yet

New activity in ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF about 5 hours ago

Compatibility with Nexesenex/croco.cpp ???

#4 opened about 9 hours ago by

New activity in ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF about 7 hours ago

Any reason why it says "pure" in the folder name pure-IQ4_XS?

#2 opened 1 day ago by

pure-IQ4_KS Error in naming

#5 opened about 8 hours ago by

New activity in ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF about 8 hours ago

jinja flag

#3 opened about 22 hours ago by

New activity in ubergarm/Kimi-K2-Instruct-GGUF about 21 hours ago

Faster TG using Draft Model!

#5 opened 1 day ago by

New activity in ikawrakow/Qwen3-30B-A3B 1 day ago

GitHub account and ik_llama.cpp are down?!

#2 opened 2 days ago by

New activity in ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF 1 day ago

Context Length

#1 opened 1 day ago by

New activity in Qwen/Qwen3-235B-A22B-Instruct-2507 1 day ago

Update README.md to fix invalid yaml

#3 opened 1 day ago by

New activity in jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v2.0-GGUF 1 day ago

Seeing some TG uplift on ik_llama.cpp

#2 opened 1 day ago by

New activity in ubergarm/Kimi-K2-Instruct-GGUF 1 day ago

Can't wait!

#1 opened 8 days ago by

Problem with the Q4 quant?

#3 opened 5 days ago by

Updating models with new recipes!

#4 opened 3 days ago by

New activity in ubergarm/Kimi-K2-Instruct-GGUF 2 days ago

Quant in ~740-700GB range

#2 opened 7 days ago by

New activity in anikifoss/Kimi-K2-Instruct-DQ4_K 2 days ago

Great quality model! Very low perplexity!

#3 opened 4 days ago by

New activity in gabriellarson/Kimi-K2-Instruct-GGUF 6 days ago

Thanks for the mainline llama.cpp PR effort!

#1 opened 9 days ago by

New activity in google/gemma-3-27b-it-qat-q4_0-unquantized 7 days ago

Some initial results comparing size and perplexity

#1 opened 3 months ago by

New activity in ubergarm/Kimi-K2-Instruct-GGUF 7 days ago

Quant in ~740-700GB range

#2 opened 7 days ago by

Can't wait!

#1 opened 8 days ago by

New activity in gabriellarson/Kimi-K2-Instruct-GGUF 7 days ago

Thanks for the mainline llama.cpp PR effort!

#1 opened 9 days ago by

Thanks for the mainline llama.cpp PR effort!

#1 opened 9 days ago by