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 1 day ago

please make some ik_llama ggufs

15

#7 opened 11 days ago by

dddgkktxmk

New activity in ubergarm/Qwen3.6-27B-GGUF 3 days ago

Vision support

👍 1

3

#4 opened 3 days ago by

toralux

How to use MTP in GGUF?

20

#2 opened 23 days ago by

Friedland

New activity in SulphurAI/Sulphur-2-base 4 days ago

distilled works fine, base doesn't

5

#14 opened 15 days ago by

AliceThirty

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

MTP support merged in llama.cpp

13

#10 opened 7 days ago by

tarruda

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

MTP Support

👍 2

9

#13 opened 7 days ago by

anikifoss

New activity in ubergarm/Qwen3-Coder-Next-GGUF 9 days ago

Quant requests?

17

#1 opened 3 months ago by

ubergarm

New activity in ubergarm/GLM-5.1-GGUF 11 days ago

Slow prompt processing?

4

#9 opened 14 days ago by

malamen4

New activity in turboderp/Qwen3.6-27B-DFlash-exl3 12 days ago

Nice Work!

❤️ 1

1

#1 opened 12 days ago by

ubergarm

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

These shoudl work on ik_llama.cpp too

🚀👍 8

#3 opened 12 days ago by

ubergarm

New activity in ubergarm/GLM-5.1-GGUF 12 days ago

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

👍 1

1

#8 opened 17 days ago by

whoisjeremylam

New activity in RDson/Qwen3.6-27B-MTP-IQ4_KS-GGUF 17 days ago

Yay more ik quants!

❤️ 1

#1 opened 17 days ago by

ubergarm

New activity in RDson/Qwen3.6-27B-MTP-Q4_K_M-GGUF 18 days ago

提速效果不理想

7

#1 opened 23 days ago by

androidli

New activity in Lorbus/Qwen3.6-27B-int4-AutoRound 18 days ago

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

👍 1

1

#4 opened 29 days ago by

Crigges

New activity in ubergarm/Qwen3.6-27B-GGUF 22 days ago

Q6_0 use over Q6_K?

2

#3 opened 22 days ago by

resynth

New activity in ubergarm/Qwen3.6-27B-GGUF 24 days ago

Great model for single GPU use cases.

🔥 4

16

#1 opened 28 days ago by

phakio

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 26 days ago

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

30

#12 opened 2 months ago by

mancub

New activity in ubergarm/Qwen3.5-35B-A3B-GGUF 29 days ago

Any plans to release Qwen3.6 ?

1

#3 opened 29 days ago by

ittokasso

New activity in ubergarm/Qwen3.5-27B-GGUF 29 days ago

smol-IQ4_NL with turboquant is outstanding for 24GB VRAM

🔥 1

3

#7 opened 30 days ago by

IHaveNoClueAndIMustPost

New activity in ubergarm/Kimi-K2.6-GGUF 29 days ago

Much faster IQ2_KS quantization PPL results?

3

#10 opened about 1 month ago by

gghfez