John Leimgruber III PRO

ubergarm's activity

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

New activity in RDson/Qwen3.6-27B-MTP-IQ4_KS-GGUF 4 days ago

Yay more ik quants!

❤️ 1

#1 opened 4 days ago by

ubergarm

liked a model 4 days ago

RDson/Qwen3.6-27B-MTP-IQ4_KS-GGUF

Text Generation • 27B • Updated 8 days ago • 21.6k • 6

New activity in RDson/Qwen3.6-27B-MTP-Q4_K_M-GGUF 5 days ago

提速效果不理想

7

#1 opened 10 days ago by

androidli

liked a model 5 days ago

Lorbus/Qwen3.6-27B-int4-AutoRound

Image-Text-to-Text • 6B • Updated 18 days ago • 481k • 92

New activity in Lorbus/Qwen3.6-27B-int4-AutoRound 5 days ago

How does this fair against other quants without MTP like unsloth?

👍 1

1

#4 opened 15 days ago by

Crigges

New activity in ubergarm/Qwen3.6-27B-GGUF 5 days ago

How to use MTP in GGUF?

18

#2 opened 10 days ago by

Friedland

liked 2 models 5 days ago

google/gemma-4-31B-it-assistant

Any-to-Any • 0.5B • Updated 5 days ago • 56.6k • 179

RDson/Qwen3.6-27B-MTP-Q4_K_M-GGUF

27B • Updated 11 days ago • 4.92k • 24

updated a model 6 days ago

ubergarm/Qwen3.6-27B-GGUF

Text Generation • 27B • Updated 6 days ago • 10.9k • 18

New activity in ubergarm/Qwen3.6-27B-GGUF 9 days ago

Q6_0 use over Q6_K?

2

#3 opened 9 days ago by

resynth

New activity in ubergarm/Qwen3.6-27B-GGUF 11 days ago

Great model for single GPU use cases.

🔥 4

16

#1 opened 15 days ago by

phakio

liked a model 13 days ago

XiaomiMiMo/MiMo-V2.5-Pro

Text Generation • 1T • Updated 2 days ago • 40.1k • 503

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 13 days ago

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

30

#12 opened about 2 months ago by

mancub

updated a model 13 days ago

ubergarm/Kimi-K2.6-GGUF

Text Generation • 1T • Updated 13 days ago • 5.79k • 35

liked a model 16 days ago

bartowski/Qwen_Qwen3.6-27B-GGUF

Image-Text-to-Text • 27B • Updated 17 days ago • 94.2k • 33

New activity in ubergarm/Qwen3.5-35B-A3B-GGUF 16 days ago

Any plans to release Qwen3.6 ?

1

#3 opened 16 days ago by

ittokasso

updated a model 16 days ago

ubergarm/Qwen3.5-27B-GGUF

Text Generation • 27B • Updated 16 days ago • 1.88k • 16

New activity in ubergarm/Qwen3.5-27B-GGUF 16 days ago

smol-IQ4_NL with turboquant is outstanding for 24GB VRAM

🔥 1

3

#7 opened 17 days ago by

IHaveNoClueAndIMustPost

published a model 16 days ago

ubergarm/Qwen3.6-27B-GGUF

Text Generation • 27B • Updated 6 days ago • 10.9k • 18

New activity in ubergarm/Kimi-K2.6-GGUF 16 days ago

Much faster IQ2_KS quantization PPL results?

3

#10 opened 17 days ago by

gghfez