pip install mistral_common

optimum-cli export executorch \
  --model "mistralai/Voxtral-Mini-3B-2507" \
  --task "multimodal-text-to-text" \
  --recipe "xnnpack" \
  --use_custom_sdpa \
  --use_custom_kv_cache \
  --max_seq_len 2048 \
  --qlinear 8da4w \
  --qlinear_encoder 8da4w \
  --qembedding 4w \
  --output_dir="voxtral"

python -m executorch.extension.audio.mel_spectrogram \
  --feature_size 128 \
  --stack_output \
  --max_audio_len 300 \
  --output_file voxtral_preprocessor.pte

./cmake-out/examples/models/voxtral/voxtral_runner \
  --model_path "model.pte" \
  --tokenizer_path "tekken.json" \
  --prompt "What can you tell me about this audio?" \
  --audio_path "audio.wav" \
  --processor_path "voxtral_preprocessor.pte" \
  --temperature 0