John Leimgruber III PRO

ubergarm's activity

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

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF about 14 hours ago

How to split this model between 2 (3) GPUs and CPU/RAM ?

16

#12 opened 4 days ago by

mancub

New activity in AesSedai/Mistral-Small-4-119B-2603-GGUF about 14 hours ago

Mistral-Small-4-119B-2603-Q5_K_M on 8 RTX 3090 with ik_llama.cpp ( compil 21 march 2026 )

❤️🔥 3

3

#1 opened about 21 hours ago by

martossien

New activity in ubergarm/Qwen3.5-27B-GGUF 1 day ago

Insight into the "weird" data.

112

#3 opened 23 days ago by

espen96

updated a model 1 day ago

ubergarm/Qwen3.5-27B-GGUF

Text Generation • 27B • Updated 1 day ago • 2.96k • 7

New activity in ubergarm/GLM-5-GGUF 1 day ago

IQ5/IQ6 Quants?

👍 1

6

#4 opened 24 days ago by

binahz

New activity in ubergarm/MiniMax-M2.5-GGUF 1 day ago

ik_llama.cpp version

9

#11 opened about 1 month ago by

geveent

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 2 days ago

Testing IQ4_KSS

4

#5 opened 25 days ago by

shewin

updated a model 2 days ago

ubergarm/Qwen3.5-122B-A10B-GGUF

Text Generation • 122B • Updated 2 days ago • 9.83k • 11

New activity in ubergarm/MiniMax-M2.5-GGUF 3 days ago

Testing IQ4_NL

13

#12 opened about 1 month ago by

shewin

New activity in AesSedai/Qwen3.5-397B-A17B-GGUF 4 days ago

IQ2_XS?

🔥 2

25

#6 opened 9 days ago by

tarruda

Dataset Imatrix

13

#7 opened 8 days ago by

Trilogix1

liked a model 5 days ago

FireRedTeam/FireRed-Image-Edit-LoRA-Zoo

Updated 18 days ago • 30

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

Appraisal

🔥 1

2

#6 opened 5 days ago by

wonderfuldestruction

liked a model 5 days ago

FireRedTeam/FireRed-Image-Edit-1.1-ComfyUI

20B • Updated 5 days ago • 11.4k • 69

New activity in ubergarm/MiniMax-M2.5-GGUF 6 days ago

8x RTX 3090, EPYC 7532, 512GB RAM: Benchmarking MiniMax-M2.5-IQ4_NL for High-Speed Coding (35-75 t/s) with opencode

🔥 2

11

#10 opened about 1 month ago by

martossien

updated a model 6 days ago

ubergarm/Qwen3.5-35B-A3B-GGUF

Text Generation • 35B • Updated 6 days ago • 7.93k • 5

New activity in sokann/Qwen3.5-27B-GGUF-4.915bpw 6 days ago

Nice work thanks for more ik_llama.cpp quants!

#1 opened 6 days ago by

ubergarm

liked a model 6 days ago

sokann/Qwen3.5-27B-GGUF-4.915bpw

27B • Updated 9 days ago • 820 • 1

New activity in ubergarm/Kimi-K2.5-GGUF 6 days ago

RPC within ik_llama

1

#6 opened 8 days ago by

x-polyglot-x

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 6 days ago

Found block with mismatching importance/model weights

1

#11 opened 9 days ago by

Thireus