Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Qwen
/
Qwen3-30B-A3B-MLX-8bit
like
8
Follow
Qwen
61.2k
Text Generation
MLX
Safetensors
qwen3_moe
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
d867092
Qwen3-30B-A3B-MLX-8bit
31.5 GB
2 contributors
History:
2 commits
littlebird13
Upload folder using huggingface_hub
d867092
verified
6 months ago
.gitattributes
1.57 kB
Upload folder using huggingface_hub
6 months ago
config.json
1.19 kB
Upload folder using huggingface_hub
6 months ago
merges.txt
1.67 MB
Upload folder using huggingface_hub
6 months ago
model-00001-of-00006.safetensors
5.25 GB
xet
Upload folder using huggingface_hub
6 months ago
model-00002-of-00006.safetensors
5.37 GB
xet
Upload folder using huggingface_hub
6 months ago
model-00003-of-00006.safetensors
5.35 GB
xet
Upload folder using huggingface_hub
6 months ago
model-00004-of-00006.safetensors
5.35 GB
xet
Upload folder using huggingface_hub
6 months ago
model-00005-of-00006.safetensors
5.37 GB
xet
Upload folder using huggingface_hub
6 months ago
model-00006-of-00006.safetensors
4.8 GB
xet
Upload folder using huggingface_hub
6 months ago
model.safetensors.index.json
120 kB
Upload folder using huggingface_hub
6 months ago
tokenizer.json
11.4 MB
xet
Upload folder using huggingface_hub
6 months ago
tokenizer_config.json
9.69 kB
Upload folder using huggingface_hub
6 months ago
vocab.json
2.78 MB
Upload folder using huggingface_hub
6 months ago
