John Leimgruber III PRO

ubergarm's activity

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

New activity in rodrigomt/s2-pro-gguf about 22 hours ago

I created an API server version of s2.cpp

👍 1

2

#4 opened 2 days ago by

mach9243

New activity in AesSedai/Qwen3.5-397B-A17B-GGUF 1 day ago

IQ2_XS?

🔥 2

29

#6 opened 11 days ago by

tarruda

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

Insight into the "weird" data.

123

#3 opened 25 days ago by

espen96

New activity in ubergarm/Qwen3.5-397B-A17B-GGUF 1 day ago

Qwen3.5-397B-A17B-IQ4_KSS on 8 RTX 3090 context 161K tokens load by ik_llama.cpp , test with opencode

🔥 1

1

#12 opened 2 days ago by

martossien

New activity in tarruda/Qwen3.5-397B-A17B-heretic-smol-IQ2_XS-GGUF 1 day ago

Any chance of IQ2_XXS? IQ2_XS is just slightly too big for Strix Halo.

6

#2 opened 2 days ago by

Cortex0833

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

ik_llama.cpp version

13

#11 opened about 1 month ago by

geveent

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

Appraisal

🔥 1

5

#6 opened 7 days ago by

wonderfuldestruction

New activity in AesSedai/Mistral-Small-4-119B-2603-GGUF 2 days ago

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

❤️🔥 3

7

#1 opened 3 days ago by

martossien

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 3 days ago

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

16

#12 opened 7 days ago by

mancub

New activity in ubergarm/GLM-5-GGUF 4 days ago

IQ5/IQ6 Quants?

👍 1

6

#4 opened 26 days ago by

binahz

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

Testing IQ4_KSS

4

#5 opened 27 days ago by

shewin

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

Testing IQ4_NL

13

#12 opened about 1 month ago by

shewin

New activity in AesSedai/Qwen3.5-397B-A17B-GGUF 6 days ago

Dataset Imatrix

16

#7 opened 10 days ago by

Trilogix1

New activity in ubergarm/MiniMax-M2.5-GGUF 8 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

12

#10 opened about 1 month ago by

martossien

New activity in sokann/Qwen3.5-27B-GGUF-4.915bpw 8 days ago

Nice work thanks for more ik_llama.cpp quants!

3

#1 opened 8 days ago by

ubergarm

New activity in ubergarm/Kimi-K2.5-GGUF 8 days ago

RPC within ik_llama

1

#6 opened 10 days ago by

x-polyglot-x

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 8 days ago

Found block with mismatching importance/model weights

1

#11 opened 11 days ago by

Thireus

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 11 days ago

Missing about 50~55GB of Q3?

5

#7 opened 26 days ago by

lingyezhixing

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 12 days ago

smol-IQ2_XS

👀 1

6

#3 opened 27 days ago by

Garf

New activity in bartowski/Qwen_Qwen3.5-9B-GGUF 12 days ago

Nice benchmark results! Great job on barto!

#2 opened 12 days ago by

ubergarm