Daniel (Unsloth) PRO

danielhanchen's activity

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

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 7 hours ago

KLD Benchmarks + why Q8_K_XL vs MXFP4 naming

👍 5

6

#11 opened 2 days ago by

danielhanchen

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 22 hours ago

Great agentic results even with IQ1_S!

👍🤗 5

1

#19 opened 1 day ago by

phakio

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 2 days ago

Pulling UD_Q8 right now, MTP questions lol

5

#3 opened 3 days ago by

Chuck572

Partially Mangled Output on LM Studio for IQ3_XXS

➕ 2

5

#9 opened 2 days ago by

miabchdave

Bug? UD-Q3_K_XL has one of the MXFP4 tensors converted to Q6_K

4

#7 opened 2 days ago by

eepos

updated a model 2 days ago

unsloth/DeepSeek-V4-Flash-0731-GGUF

284B • Updated 2 days ago • 48.7k • 371

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 3 days ago

UD-Q4_K_XL: incoherent output past short generations on Blackwell sm120 — suspected missing SwiGLU clamp (unverified)

1

#5 opened 3 days ago by

tlanderso

Run DeepSeek-V4-Flash-0731 in Unsloth! 🦥♥️

👍🔥 16

8

#6 opened 3 days ago by

danielhanchen

updated a collection 3 days ago

Unsloth Dynamic 2.0 Quants

Collection

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 113 items • Updated 2 days ago • 786

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 3 days ago

Lossless UD-Q8_K_XL. UD-Q4_K_XL also provided for now

❤️🔥 15

10

#2 opened 3 days ago by

danielhanchen

liked a model 3 days ago

unsloth/DeepSeek-V4-Flash-0731-GGUF

284B • Updated 2 days ago • 48.7k • 371

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 3 days ago

Awww yiss

🚀🔥 25

10

#1 opened 3 days ago by

CurbStomper

updated a model 3 days ago

unsloth/DeepSeek-V4-Flash-0731

Text Generation • 304B • Updated 3 days ago • 1.25k • 29

published a model 3 days ago

unsloth/DeepSeek-V4-Flash-0731-GGUF

284B • Updated 2 days ago • 48.7k • 371

New activity in unsloth/Inkling-Small-GGUF 3 days ago

Does it support image input?

👍 4

1

#1 opened 3 days ago by

SlavikF

posted an update 3 days ago

view post

Post

792

We compared 1-bit Kimi K3 to Claude Opus 5 and GPT 5.6. 🤯

We gave 4 models the same prompt: Create a glass aquarium whose side panel develops a visible crack and then bursts...

1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s.

GGUF: unsloth/Kimi-K3-GGUF
GitHub repo: https://github.com/unslothai/unsloth

See translation

• 

• 
• 1 reply

·

👍

1

1

🔥

1

1

🤗

1

1

+

Reply

replied to their post 3 days ago

view reply

Which ones? We are working on even smaller ones

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 3 days ago

Congrats on #2 model on Hugging Face!! 🔥

❤️👍 14

2

#57 opened 3 days ago by

danielhanchen

New activity in unsloth/Inkling-Small-GGUF 3 days ago

here is a guide

🔥 2

1

#2 opened 3 days ago by

gopi87

updated a model 3 days ago

unsloth/Inkling-Small-GGUF

Image-Text-to-Text • 264B • Updated 3 days ago • 25.2k • 72