no

Rotating's activity

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

New activity in unsloth/GLM-4.7-GGUF 2 months ago

"model has unused tensor" on UD-IQ2_M

1

#4 opened 2 months ago by

tarruda

New activity in unsloth/Qwen-Image-Edit-2511-GGUF 2 months ago

They sent us a Christmas turkey.

2

#1 opened 2 months ago by

Rotating

Dec 26: Updated to work for stablediffusion.cpp. And apply index_timestep_zero metadata for ComfyUI

👍 8

9

#6 opened 2 months ago by

danielhanchen

New activity in Tongyi-MAI/Z-Image-Turbo 3 months ago

fp8 text encoder pls

2

#23 opened 3 months ago by

JorG941

New activity in unsloth/Kimi-K2-Thinking-GGUF 3 months ago

No thinking tags when it runs?

13

#1 opened 4 months ago by

Disdrix

New activity in unsloth/Kimi-K2-Thinking-GGUF 4 months ago

Quantization destroyed coding abilities in Q5 (735Gb RAM)

17

#4 opened 4 months ago by

krustik

New activity in unsloth/GLM-4.6-GGUF 5 months ago

Fingers crossed for the 4.6-air

➕ ❤️ 6

14

#1 opened 5 months ago by

aaron-newsome

New activity in bartowski/zai-org_GLM-4.6-GGUF 5 months ago

Quants without imatrix

17

#2 opened 5 months ago by

Rotating

New activity in unsloth/GLM-4.5-GGUF 7 months ago

Version Q4 K XL works great with llama.cpp

🔥 1

2

#3 opened 7 months ago by

jeffwadsworth

New activity in unsloth/Kimi-K2-Instruct-GGUF 7 months ago

Update the instructions on requirements

2

#10 opened 7 months ago by

segmond

New activity in unsloth/DeepSeek-R1-0528-GGUF 9 months ago

Update - Tool Calling + Chat Template bug fixes

9

#20 opened 9 months ago by

danielhanchen

Please share feedback here!

34

#6 opened 9 months ago by

shimmyshimmer

invalid model: tensor 'blk.25.ffn_gate_exps.weight' is duplicated

2

#12 opened 9 months ago by

Rotating

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct 11 months ago

DOA

👍 1

15

#1 opened 11 months ago by

MrDevolver

New activity in unsloth/DeepSeek-V3-0324-GGUF 11 months ago

671B params or 685B params?

6

#8 opened 11 months ago by

createthis

Would There be Dynamic Qunatized Versions like 2.51bit

8

#1 opened 11 months ago by

MotorBottle

New activity in bartowski/Qwen_QwQ-32B-GGUF 12 months ago

Something wrong

12

#3 opened 12 months ago by

wcde

New activity in unsloth/DeepSeek-R1-GGUF about 1 year ago

Q2_K_XL model is the best? IQ2_XXS is better than Q2_K_XL in mmlu-pro benchmark

11

#36 opened about 1 year ago by

albertchow

is it uncensored?

5

#33 opened about 1 year ago by

Morrigan-Ship

when using with ollama, does it support kv_cache_type=q4_0 and flash_attention=1?

3

#28 opened about 1 year ago by

leonzy04