Ran Le

leran1995's activity

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

New activity in Nanbeige/Nanbeige4.2-3B 2 days ago

Why is it much slower and much more memory hungry than slightly larger models such as Qwen3.5-4B?

3

#31 opened 4 days ago by

slightlyoutofphase

GPQA复现上出现问题

2

#30 opened 5 days ago by

BShooter

New activity in Nanbeige/Nanbeige4.2-3B 6 days ago

General Release Date for 4.5?

2

#29 opened 6 days ago by

Katsugachi

Tested on the Artificial Analysis Intelligence Index?

👀 2

2

#25 opened 14 days ago by

ATHENIS

updated a collection 11 days ago

Nanbeige4.2-3B

Collection

6 items • Updated 7 days ago • 6

published 2 models 11 days ago

Nanbeige/Nanbeige4.2-3B-FP8

Text Generation • 4B • Updated 11 days ago • 136 • 8

Nanbeige/Nanbeige4.2-3B-GPTQ-Int8

Text Generation • 2B • Updated 11 days ago • 118 • 3

updated 2 models 11 days ago

Nanbeige/Nanbeige4.2-3B-FP8

Text Generation • 4B • Updated 11 days ago • 136 • 8

Nanbeige/Nanbeige4.2-3B-GPTQ-Int8

Text Generation • 2B • Updated 11 days ago • 118 • 3

New activity in Nanbeige/Nanbeige4.2-3B 14 days ago

Pretrain recipe questions for small-model compute budgeting (not data)

👀 1

1

#26 opened 14 days ago by

Infatoshi

updated 2 models 16 days ago

Nanbeige/Nanbeige4.2-3B

Text Generation • 4B • Updated 16 days ago • 61.7k • 706

Nanbeige/Nanbeige4.2-3B-Base

Text Generation • 4B • Updated 16 days ago • 3.65k • 57

New activity in Nanbeige/Nanbeige4.2-3B 17 days ago

Awesome!

👍 2

1

#24 opened 17 days ago by

AsThirtyThree

New activity in Nanbeige/Nanbeige4.2-3B 20 days ago

Amazing for its size, but spirals into questionable solutions once it fails something

1

#21 opened 20 days ago by

Mk2Oracle

New activity in Nanbeige/Nanbeige4.2-3B 22 days ago

Massive activation at layer 21, and three follow-ups on loop depth + LoopSplit

1

#20 opened 22 days ago by

an0nya

Suitability for 8 GB graphics cards

👀 4

3

#18 opened 22 days ago by

thermi6