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 23 hours ago

DSpark enables DeepSeek to run 2x Faster!

🤗🔥 2

1

#36 opened about 23 hours ago by

danielhanchen

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 4 days ago

dspark-DeepSeek-V4-Flash-0731-Q8_0.gguf FAILS to load in the latest llama-server

➕ 1

5

#26 opened 4 days ago by

Nerdsking

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 5 days ago

KLD Benchmarks + why Q8_K_XL vs MXFP4 naming

❤️👍 10

6

#11 opened 6 days ago by

danielhanchen

Great agentic results even with IQ1_S!

👍🤗 8

5

#19 opened 5 days ago by

phakio

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 6 days ago

Pulling UD_Q8 right now, MTP questions lol

5

#3 opened 7 days ago by

Chuck572

Partially Mangled Output on LM Studio for IQ3_XXS

➕ 2

5

#9 opened 7 days ago by

miabchdave

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

4

#7 opened 7 days ago by

eepos

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

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

1

#5 opened 7 days ago by

tlanderso

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

👍🔥 16

8

#6 opened 7 days ago by

danielhanchen

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

❤️🔥 15

10

#2 opened 7 days ago by

danielhanchen

Awww yiss

🚀🔥 26

10

#1 opened 7 days ago by

CurbStomper

New activity in unsloth/Inkling-Small-GGUF 7 days ago

Does it support image input?

👍 4

1

#1 opened 8 days ago by

SlavikF

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 7 days ago

Congrats on #2 model on Hugging Face!! 🔥

❤️👍 22

2

#57 opened 7 days ago by

danielhanchen

New activity in unsloth/Inkling-Small-GGUF 7 days ago

here is a guide

🔥 3

1

#2 opened 7 days ago by

gopi87

New activity in unsloth/Kimi-K3-GGUF 8 days ago

UD-Q2_K_XL release?

6

#4 opened 10 days ago by

Deniz-Eren

THERES NO GGUFS

🔥 4

19

#2 opened 11 days ago by

GGUFGuy

llama.cpp support?

1

#1 opened 11 days ago by

kimi-chan

Model size: 0.4B params?

6

#3 opened 10 days ago by

EinNeuling

Independent structural validation of Kimi K3 UD-IQ1_M and UD-Q4_K_XL

#13 opened 8 days ago by

200lz

1-bit Kimi K3 vs Claude Opus 5 vs GPT 5.6

👀🚀 20

22

#12 opened 9 days ago by

danielhanchen