Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
majentik
/
gpt-oss-20b-RotorQuant-MLX-8bit
like
0
Text Generation
MLX
Safetensors
gpt_oss
rotorquant
kv-cache-quantization
gpt-oss
openai
Mixture of Experts
quantized
8bit
conversational
4-bit precision
arxiv:
2504.19874
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
gpt-oss-20b-RotorQuant-MLX-8bit
/
generation_config.json
Commit History
Add MLX quantized model
20a07b8
verified
majentik
commited on
1 day ago
majentik commited on 