Unsloth AI

unsloth's activity

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

danielhanchen 

in unsloth/Kimi-K2.5-GGUF about 5 hours ago

Can you make a REAP verson at 50

1

#4 opened 1 day ago by

infinityai

danielhanchen 

in unsloth/DeepSeek-V3.2-GGUF about 16 hours ago

Does this support DSA/lighting attention?

4

#1 opened 1 day ago by

segmond

Already testing it

🔥 1

1

#2 opened about 17 hours ago by

Trilogix1

danielhanchen 

in unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF about 20 hours ago

New Refresh with added Tool Calling in calibration dataset and improved imatrix

❤️ 6

8

#21 opened 1 day ago by

danielhanchen

danielhanchen 

updated a model about 22 hours ago

unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF

Text Generation • 31B • Updated about 22 hours ago • 107k • 427

danielhanchen 

in unsloth/Kimi-K2.5-GGUF 1 day ago

Q4_K_S versus Q3_K_XL

1

#3 opened 1 day ago by

segmond

danielhanchen 

updated a model 1 day ago

unsloth/DeepSeek-V3.2-GGUF

671B • Updated about 14 hours ago • 204 • 6

danielhanchen 

updated 2 models 2 days ago

unsloth/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated 2 days ago • 5.14k • 21

unsloth/DeepSeek-V3.2

Text Generation • 685B • Updated 1 day ago • 65 • 8

danielhanchen 

in unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF 2 days ago

Performance is poor

10

#1 opened 6 days ago by

sainnhe

danielhanchen 

updated a model 2 days ago

unsloth/DeepSeek-OCR-2

Image-Text-to-Text • 3B • Updated 2 days ago • 2.65k • 14

danielhanchen 

in unsloth/DeepSeek-OCR-2 2 days ago

Unsloth implementation

3

#1 opened 4 days ago by

Kernel

danielhanchen 

in unsloth/Trinity-Large-Preview-GGUF 2 days ago

Quantasation for Ming-flash-omni-Preview?

1

#1 opened 3 days ago by

facehuggerfromspace

danielhanchen 

published a model 2 days ago

unsloth/DeepSeek-V3.2-GGUF

671B • Updated about 14 hours ago • 204 • 6

danielhanchen 

updated a model 2 days ago

unsloth/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4

Text Generation • 18B • Updated 2 days ago • 25 • 2

danielhanchen 

published a model 2 days ago

unsloth/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4

Text Generation • 18B • Updated 2 days ago • 25 • 2

danielhanchen 

updated 2 models 2 days ago

unsloth/Kimi-K2.5-GGUF

1T • Updated 2 days ago • 8.75k • 129

unsloth/Trinity-Large-Preview-GGUF

399B • Updated 2 days ago • 919 • 9

danielhanchen 

posted an update 3 days ago

view post

Post

3095

You can now run Kimi K2.5 locally! 🔥

We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.

GGUF: unsloth/Kimi-K2.5-GGUF

Guide: https://unsloth.ai/docs/models/kimi-k2.5

See translation

• 
• 

• 
• 
• 
• 7 replies

·

🚀

15

15

😎

3

3

🔥

2

2

👀

1

1

+

Reply

danielhanchen 

updated a model 3 days ago

unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF

Text Generation • 23B • Updated 3 days ago • 24.9k • 93