68 15 178

John Leimgruber III

ubergarm

https://emptyduck.com

ubergarm

AI & ML interests

Open LLMs and Astrophotography image processing.

Recent Activity

new activity about 20 hours ago

ubergarm/Qwen3-235B-A22B-GGUF:Context Length

new activity 3 days ago

ubergarm/Qwen3-235B-A22B-GGUF:Q6 K

new activity 4 days ago

ubergarm/DeepSeek-V3-0324-GGUF:Guide on how to spread the model across 2 GPUs?

View all activity

Organizations

None yet

ubergarm's activity

New activity in ubergarm/Qwen3-235B-A22B-GGUF about 20 hours ago

Context Length

#2 opened 1 day ago by

vacekj

New activity in ubergarm/Qwen3-235B-A22B-GGUF 3 days ago

Q6 K

#1 opened 7 days ago by

Autumnlight

New activity in ubergarm/DeepSeek-V3-0324-GGUF 4 days ago

Guide on how to spread the model across 2 GPUs?

#3 opened 4 days ago by

eagerexecution

New activity in ikawrakow/Qwen3-30B-A3B 5 days ago

Thanks!

#1 opened 5 days ago by

ubergarm

New activity in bartowski/Qwen_Qwen3-30B-A3B-GGUF 5 days ago

What are folks opinion on 4KM quants? Are they viable?

#3 opened 8 days ago by

Permahuman

New activity in ubergarm/Qwen3-30B-A3B-GGUF 5 days ago

Appreciation.

#1 opened 6 days ago by

atopwhether

New activity in ArtusDev/Qwen3-235B-A22B-GGUF 6 days ago

Imitation is the highest form of flattery.

#1 opened 6 days ago by

ubergarm

New activity in unsloth/Phi-4-reasoning-plus-GGUF 6 days ago

dynamic quants

#1 opened 6 days ago by

lucyknada

New activity in Qwen/Qwen3-30B-A3B 6 days ago

AWQ quantized model support timeline?

#12 opened 8 days ago by

hyunw55

New activity in unsloth/QwQ-32B-unsloth-bnb-4bit 7 days ago

How to use the bnb-4bit model?

#4 opened 2 months ago by

neoragex2002

New activity in unsloth/DeepSeek-V3-0324-GGUF-UD 12 days ago

Thank you but some issues

#2 opened 15 days ago by

MB7977

New activity in ubergarm/gemma-3-27b-it-qat-GGUF 13 days ago

Compare to new Dynamic v2.0 Unsloth quants ?

#2 opened 14 days ago by

BernardH

New activity in ubergarm/DeepSeek-V3-0324-GGUF 13 days ago

Expected speed in some known hardware - data required

#1 opened about 1 month ago by

mechanicmuthu

New activity in ubergarm/DeepSeek-V3-0324-GGUF 14 days ago

Comparing to new Dynamic v2.0 Unlsoth quants ?

#2 opened 14 days ago by

BernardH

New activity in ubergarm/gemma-3-27b-it-qat-GGUF 16 days ago

Try to install for ollama but got errors

#1 opened 16 days ago by

shilik

New activity in Comfy-Org/HiDream-I1_ComfyUI 17 days ago

Can we have a Llama-3.1-8B-Lexi-Uncensored-V2_fp8_scaled.safetensors

#10 opened 22 days ago by

drguolai

New activity in bartowski/google_gemma-3-27b-it-qat-GGUF 18 days ago

Other Imatrix quants (IQ3_XS) ?

#1 opened 19 days ago by deleted

New activity in city96/HiDream-I1-Full-gguf 19 days ago

Can we use existed llama 3.1 gguf

#1 opened 22 days ago by

CHNtentes

New activity in google/gemma-3-27b-it-qat-q4_0-unquantized 19 days ago

Some initial results comparing size and perplexity

#1 opened 20 days ago by

ubergarm

New activity in google/gemma-3-12b-it-qat-q4_0-gguf 20 days ago

Permission to access the Unquantized versions of the QAT weights for Gemma-3

#4 opened about 1 month ago by

Joseph717171