Shuasimodo

Shuasimodo's activity

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

New activity in noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF about 8 hours ago

Increasing the precision of some of the weights when quantizing

👍 3

44

#2 opened 5 days ago by

Shuasimodo

upvoted an article 1 day ago

view article

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

• 
• 
• +4

2 days ago

•

249

updated a collection 2 days ago

High Quality Models

Collection

Smaller quantized models that generate a high quality output. • 2 items • Updated 2 days ago

New activity in noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF 2 days ago

BF16 has looping issues

28

#4 opened 3 days ago by

jmander11

liked a model 4 days ago

noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF

Text Generation • 80B • Updated 2 days ago • 10.1k • 16

New activity in Qwen/Qwen3-Coder-Next 5 days ago

model with thinking?

➕ 2

6

#5 opened 18 days ago by

pypry

New activity in unsloth/MiniMax-M2.5-GGUF 5 days ago

4-bit quantization: MXFP4_MOE vs Q4_K_XL?

4

#3 opened 7 days ago by

fsaudm