cohere-transcribe-03-2026-mlx-fp16

Converted MLX fp16 weights for CohereLabs/cohere-transcribe-03-2026.

Files

  • model.safetensors โ€” converted MLX weights (cohere_transcribe_mlx.safetensors)
  • config.json
  • tokenizer.model
  • tokenizer_config.json
  • preprocessor_config.json
  • special_tokens_map.json
  • key_map.json โ€” conversion key mapping
  • conversion_summary.json โ€” conversion metadata summary

Notes

  • This repository contains conversion artifacts only.
  • Refer to the upstream model card and license in CohereLabs/cohere-transcribe-03-2026 for usage/licensing details.
Downloads last month
248
Safetensors
Model size
2B params
Tensor type
F16
ยท
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support