Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Teaspoon-AI
/
Voxtral-Mini-4B-INT4-Jetson

speech-to-text
voxtral
mistral
int4
quantized
marlin
jetson
edge
realtime
streaming
Model card Files Files and versions
xet
Community
Voxtral-Mini-4B-INT4-Jetson / scripts
53.8 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
tsp-stefano's picture
tsp-stefano
Single-file Marlin INT4: direct RTN quantization, no GPTQ intermediate
22a85ee verified about 1 month ago
  • jetson_serve_sdpa.py
    43.9 kB
    Single-file Marlin INT4: direct RTN quantization, no GPTQ intermediate about 1 month ago
  • quantize_marlin.py
    9.88 kB
    Single-file Marlin INT4: direct RTN quantization, no GPTQ intermediate about 1 month ago