Ryuichi Leo Takashige

RyuichiLT's activity

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

New activity in mlx-community/Nemotron-3-Ultra-550B-A55B 3 days ago

Getting gibberish output with TP in EXO

20

#1 opened 6 days ago by

sjthapa

updated 2 models 4 days ago

mlx-community/DeepSeek-V4-Flash

Text Generation • 284B • Updated 4 days ago • 5.66k • 1

mlx-community/DeepSeek-V4-Pro

Text Generation • 1.6T • Updated 4 days ago • 3.03k

updated 2 models 6 days ago

mlx-community/Nemotron-3-Ultra-550B-A55B-4bit

Text Generation • 105B • Updated 6 days ago • 939 • 2

mlx-community/Nemotron-3-Ultra-550B-A55B

Text Generation • 108B • Updated 6 days ago • 417

published a model 7 days ago

mlx-community/Nemotron-3-Ultra-550B-A55B-4bit

Text Generation • 105B • Updated 6 days ago • 939 • 2

updated a model 7 days ago

mlx-community/Nemotron-3-Ultra-550B-A55B-bf16

Text Generation • Updated 7 days ago

published 2 models 7 days ago

mlx-community/Nemotron-3-Ultra-550B-A55B

Text Generation • 108B • Updated 6 days ago • 417

mlx-community/Nemotron-3-Ultra-550B-A55B-bf16

Text Generation • Updated 7 days ago

updated a model 12 days ago

exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MTP-mlx

3B • Updated 12 days ago

published a model 12 days ago

exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MTP-mlx

3B • Updated 12 days ago

updated a model 13 days ago

exolabs/Qwen3.6-27B-MTP-mlx

0.4B • Updated 13 days ago

published a model 13 days ago

exolabs/Qwen3.6-27B-MTP-mlx

0.4B • Updated 13 days ago

published 2 models about 2 months ago

mlx-community/DeepSeek-V4-Pro

Text Generation • 1.6T • Updated 4 days ago • 3.03k

mlx-community/DeepSeek-V4-Flash

Text Generation • 284B • Updated 4 days ago • 5.66k • 1

updated a model about 2 months ago

exolabs/Kimi-K2.6-vision

Updated Apr 23 • 2.01k • 1

published a model about 2 months ago

exolabs/Kimi-K2.6-vision

Updated Apr 23 • 2.01k • 1

updated 2 models 2 months ago

mlx-community/GLM-5.1-MXFP4-Q8

Text Generation • 744B • Updated Apr 8 • 2.48k • 4

mlx-community/GLM-5.1-8bit-MXFP8

Updated Apr 8 • 29

published a model 2 months ago

mlx-community/GLM-5.1-MXFP4-Q8

Text Generation • 744B • Updated Apr 8 • 2.48k • 4