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

  • Log In
  • Sign Up

NeoRoth
/
voxtral-3b-quantized

MLX
Safetensors
voxtral
quantized
voxtral-mini-3b-2507
Model card Files Files and versions
xet
Community
voxtral-3b-quantized / mlx-q6
4.31 GB
  • 1 contributor
History: 1 commit
NeoRoth's picture
NeoRoth
Update mlx-q6 (q_bits=6, group=64) @ 2025-08-26 17:28 UTC
0894dbb verified 5 months ago
  • config.json
    1.4 kB
    Update mlx-q6 (q_bits=6, group=64) @ 2025-08-26 17:28 UTC 5 months ago
  • generation_config.json
    108 Bytes
    Update mlx-q6 (q_bits=6, group=64) @ 2025-08-26 17:28 UTC 5 months ago
  • model-00001-of-00001.safetensors
    4.29 GB
    xet
    Update mlx-q6 (q_bits=6, group=64) @ 2025-08-26 17:28 UTC 5 months ago
  • model.safetensors.index.json
    68.1 kB
    Update mlx-q6 (q_bits=6, group=64) @ 2025-08-26 17:28 UTC 5 months ago
  • params.json
    731 Bytes
    Update mlx-q6 (q_bits=6, group=64) @ 2025-08-26 17:28 UTC 5 months ago
  • preprocessor_config.json
    357 Bytes
    Update mlx-q6 (q_bits=6, group=64) @ 2025-08-26 17:28 UTC 5 months ago
  • tekken.json
    14.9 MB
    xet
    Update mlx-q6 (q_bits=6, group=64) @ 2025-08-26 17:28 UTC 5 months ago