Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Qwen
/
Qwen3-4B-MLX-8bit
like
2
Follow
Qwen
56k
Text Generation
MLX
Safetensors
qwen3
conversational
8-bit precision
arxiv:
2309.00071
arxiv:
2505.09388
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Use this model
main
Qwen3-4B-MLX-8bit
Commit History
Create LICENSE
315fb48
verified
littlebird13
commited on
Jul 7
Update README.md
70b51db
verified
littlebird13
commited on
Jun 26
Update README.md
66f52c8
verified
littlebird13
commited on
Jun 15
Update README.md
027495c
verified
JustinLin610
commited on
Jun 14
Update README.md
9fea2fb
verified
JustinLin610
commited on
Jun 14
Update README.md
fae91d3
verified
JustinLin610
commited on
Jun 14
Update README.md
d50af91
verified
JustinLin610
commited on
Jun 14
Update README.md
344fe37
verified
JustinLin610
commited on
Jun 14
Create README.md
a8246ff
verified
littlebird13
commited on
Jun 13
Upload folder using huggingface_hub
7251946
verified
littlebird13
commited on
May 23
initial commit
5b53f6a
verified
littlebird13
commited on
May 23