Daniel (Unsloth) PRO

danielhanchen's activity

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

liked a model about 7 hours ago

VideoRebirthAI/hyperflow-h3-flash

Image-Text-to-Video • 14B • Updated 1 day ago • 496k • 301

New activity in unsloth/DeepSeek-V4.1-Flash-1017-GGUF about 8 hours ago

Document swapping the Engram table with llama.cpp --ple

#17 opened 2 days ago by

oobabooga

posted an update about 8 hours ago

view post

Post

71

We released DeepSeek-V4.1-Flash-1017 Dynamic v3.1 GGUFs which rank #1 on Terminal Bench, DeepSWE & more on 512K context.

1-bit Unsloth GGUF scores 68.1 on DeepSWE, 72.2 on Terminal-Bench, 52.7 on AutomationBench. >10% ahead of other quants.

GGUF: unsloth/DeepSeek-V4.1-Flash-1017-GGUF

See translation

• 
• 
• 

Reply

updated a model about 21 hours ago

unsloth/Inkling-2-Small-GGUF

Image-Text-to-Text • 594B • Updated about 21 hours ago • 4.16k • 12

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 2 days ago

Stopping issues with new 3.1 UD quants

6

#106 opened 3 days ago by

tmsel

published a model 2 days ago

unsloth/MiniMax-H3-Image-GGUF

Text-to-Image • 20B • Updated 2 days ago • 4.88k • 11

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 2 days ago

Please ensure that significant drops in speed do not occur in new versions of Quants.

1

#105 opened 3 days ago by

Vinyl86

New activity in unsloth/Qwen3.8-27B-GGUF 2 days ago

Uniform GGUF quants silently break Qwen3.8-27B's deep thinking — reproduced on llama.cpp AND vLLM (short tasks unaffected)

👍🧠 1

12

#135 opened about 1 month ago by

Jerryccccc

updated a model 2 days ago

unsloth/MiniMax-H3-Image-GGUF

Text-to-Image • 20B • Updated 2 days ago • 4.88k • 11

published a model 2 days ago

unsloth/Inkling-2-Small-GGUF

Image-Text-to-Text • 594B • Updated about 21 hours ago • 4.16k • 12

liked a model 3 days ago

unsloth/Qwen3.8-27B-GGUF

27B • Updated 3 days ago • 6.57M • 5.97k

New activity in unsloth/Qwen3.8-27B-GGUF 3 days ago

Introducing Qwen3.8-27B Unsloth Dynamic v3.1 GGUFs!

🤗❤️ 13

9

#143 opened 4 days ago by

danielhanchen

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 3 days ago

Introducing Qwen3.8-Flash Unsloth Dynamic v3.1 GGUFs!

❤️🚀 20

19

#91 opened 11 days ago by

danielhanchen

A quick question

1

#104 opened 4 days ago by

CHTL85

updated a model 3 days ago

unsloth/Qwen3.8-27B-GGUF

27B • Updated 3 days ago • 6.57M • 5.97k

New activity in unsloth/Qwen3.8-27B-GGUF 3 days ago

Qwen3.8-27B-UD-IQ3_S.gguf is still old one

1

#144 opened 4 days ago by

naildirect

New activity in unsloth/Qwen3.8-27B-GGUF 4 days ago

Introducing Unsloth Dynamic v3 Qwen3.8

👍🔥 56

40

#74 opened 3 months ago by

danielhanchen

posted an update 4 days ago

view post

Post

7,727

Today, we're releasing the highest accuracy Qwen3.8-27B GGUFs!

Our new Dynamic V3.1 GGUFs lead by 5–10% on average across Terminal Bench, DeepSWE & more. We’re working on an even better version for Qwen4.

Run on 12GB RAM setups

GGUF: unsloth/Qwen3.8-27B-GGUF
Blog: https://unsloth.ai/docs/models/qwen3.8

See translation

• 
• 

🔥

18

18

❤️

10

10

🤯

2

2

🚀

1

1

🤗

1

1

😔

1

1

🧠

1

1

👍

1

1

+

Reply

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 4 days ago

IQ3_XXS is insane and probably the best size to quality ratio

🔥🤗 9

5

#102 opened 6 days ago by

dandandelion