John Leimgruber III PRO

ubergarm's activity

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

New activity in ubergarm/Kimi-K2.6-GGUF about 1 hour ago

The Best Kimi Quant!

🔥 1

2

#1 opened about 3 hours ago by

anikifoss

liked a model about 3 hours ago

AesSedai/Kimi-K2.6-GGUF

1T • Updated about 3 hours ago • 6

updated a model about 4 hours ago

ubergarm/Kimi-K2.6-GGUF

Text Generation • 1T • Updated about 2 hours ago • 17

published a model about 11 hours ago

ubergarm/Kimi-K2.6-GGUF

Text Generation • 1T • Updated about 2 hours ago • 17

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

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

22

#12 opened about 1 month ago by

mancub

New activity in AesSedai/Qwen3.6-35B-A3B-GGUF about 12 hours ago

Imatrix and Mmprojs degrade quality

8

#2 opened 4 days ago by

Trilogix1

New activity in ubergarm/MiniMax-M2.5-GGUF about 12 hours ago

ik_llama.cpp version

17

#11 opened 2 months ago by

geveent

New activity in ubergarm/Step-3.5-Flash-GGUF about 12 hours ago

Comparison with APEX quants

1

#14 opened 1 day ago by

FBykov

New activity in ubergarm/MiniMax-M2.7-GGUF about 12 hours ago

Testing IQ5_K

❤️ 1

10

#8 opened 7 days ago by

shewin

liked a model about 13 hours ago

moonshotai/Kimi-K2.6

Image-Text-to-Text • 1.1T • Updated about 3 hours ago • 423 • • 459

New activity in ubergarm/GLM-5.1-GGUF about 13 hours ago

render_message_to_json: Neither string content nor typed content is supported by the template. This is unexpected and may lead to issues.

4

#7 opened 5 days ago by

whoisjeremylam

New activity in ubergarm/MiniMax-M2.7-GGUF 3 days ago

Testing Q5 flavors (ubergarm / aessedai / unsloth) for "speed" on 8x RTX 3090

🔥 1

1

#10 opened 4 days ago by

dehnhaide

4 bpw suggestions

👀 1

18

#1 opened 8 days ago by

ndroidph

New activity in ubergarm/GLM-5.1-GGUF 3 days ago

Testing smol-IQ4_K

8

#4 opened 11 days ago by

shewin

liked a model 4 days ago

AesSedai/Qwen3.6-35B-A3B-GGUF

35B • Updated 2 days ago • 7.22k • 22

updated a model 6 days ago

ubergarm/MiniMax-M2.7-GGUF

Text Generation • 229B • Updated 6 days ago • 4.15k • 17

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

Why the fp32 tensors in the IQ5_KS quant?

3

#14 opened 7 days ago by

KeinNiemand

liked 2 models 6 days ago

KeinNiemand/Qwen3.5-122B-A10B-IK_GGUF

Text Generation • 122B • Updated Mar 13 • 114 • 1

KeinNiemand/Qwen3.5-122B-A10B-abliterix-IK_GGUF

Text Generation • 122B • Updated 7 days ago • 2.77k • 1

New activity in ubergarm/GLM-5.1-GGUF 7 days ago

GLM 5.1 vs GLM 5 - burns A LOT output tokens on thinking

👍 1

33

#6 opened 10 days ago by

curiouspp8