John Leimgruber III PRO

ubergarm's activity

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

New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF about 4 hours ago

please make some ik_llama ggufs

8

#7 opened 1 day ago by

dddgkktxmk

New activity in ubergarm/Qwen3-Coder-Next-GGUF about 5 hours ago

Quant requests?

14

#1 opened 3 months ago by

ubergarm

New activity in ubergarm/GLM-5.1-GGUF 1 day ago

Slow prompt processing?

4

#9 opened 4 days ago by

malamen4

New activity in turboderp/Qwen3.6-27B-DFlash-exl3 2 days ago

Nice Work!

❤️ 1

1

#1 opened 2 days ago by

ubergarm

New activity in unsloth/Qwen3.6-27B-MTP-GGUF 2 days ago

These shoudl work on ik_llama.cpp too

👍🚀 6

#3 opened 2 days ago by

ubergarm

New activity in ubergarm/GLM-5.1-GGUF 2 days ago

Draft llama.cpp PR for DSA (Deepseek Sparse Attention)

👍 1

1

#8 opened 7 days ago by

whoisjeremylam

New activity in RDson/Qwen3.6-27B-MTP-IQ4_KS-GGUF 7 days ago

Yay more ik quants!

❤️ 1

#1 opened 7 days ago by

ubergarm

New activity in RDson/Qwen3.6-27B-MTP-Q4_K_M-GGUF 8 days ago

提速效果不理想

7

#1 opened 14 days ago by

androidli

New activity in Lorbus/Qwen3.6-27B-int4-AutoRound 8 days ago

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

👍 1

1

#4 opened 19 days ago by

Crigges

New activity in ubergarm/Qwen3.6-27B-GGUF 8 days ago

How to use MTP in GGUF?

18

#2 opened 13 days ago by

Friedland

New activity in ubergarm/Qwen3.6-27B-GGUF 12 days ago

Q6_0 use over Q6_K?

2

#3 opened 12 days ago by

resynth

New activity in ubergarm/Qwen3.6-27B-GGUF 14 days ago

Great model for single GPU use cases.

🔥 4

16

#1 opened 19 days ago by

phakio

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 16 days ago

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

30

#12 opened about 2 months ago by

mancub

New activity in ubergarm/Qwen3.5-35B-A3B-GGUF 19 days ago

Any plans to release Qwen3.6 ?

1

#3 opened 19 days ago by

ittokasso

New activity in ubergarm/Qwen3.5-27B-GGUF 19 days ago

smol-IQ4_NL with turboquant is outstanding for 24GB VRAM

🔥 1

3

#7 opened 20 days ago by

IHaveNoClueAndIMustPost

New activity in ubergarm/Kimi-K2.6-GGUF 19 days ago

Much faster IQ2_KS quantization PPL results?

3

#10 opened 20 days ago by

gghfez

really awesome speeds! running at 256k context.

🔥 1

5

#11 opened 20 days ago by

mtcl

Is IQ3_K mainline compatible?

1

#12 opened 20 days ago by

TimothyRoo

New activity in ubergarm/Kimi-K2.6-GGUF 20 days ago

Testing IQ3_K

🔥 1

8

#6 opened 21 days ago by

shewin

How to disable thinking?

4

#9 opened 21 days ago by

Hansi2024