Omi Med STT v1 MLX q8
Apple Silicon q8 export of Omi Med STT v1.
This is the default Mac artifact used by the omi-med-stt CLI. It is much
smaller than the full MLX export and keeps very similar benchmark quality.
Quickstart
pip install -U "omi-med-stt[mlx]"
omi-med-stt audio.wav
Explicit selection:
omi-med-stt audio.wav --runtime mlx --model omi-health/omi-med-stt-v1-mlx-q8
Evaluation
The public weights are unchanged. These September 2026 results come from the current documented runtime recipes on the same frozen 1,513-clip, 7.18-hour medical benchmark and scorer. No dictionary, custom vocabulary, contextual bias, reference-aware selection, or transcript correction was used.
| Runtime artifact | Platform | WER | M-WER | Drug M-WER | Medical recall |
|---|---|---|---|---|---|
| NeMo canonical | NVIDIA CUDA (L4, BF16) | 6.54% | 2.23% | 4.75% | 97.77% |
| MLX q8 | Apple Silicon (M4 Max) | 6.65% | 2.12% | 4.52% | 97.88% |
| GGUF q8_0 | Linux/Windows CPU | 7.10% | 2.16% | 4.30% | 97.84% |
Lower is better for the error rates; higher is better for medical recall. MLX q8 remains the Mac default because it combines the strongest canonical M-WER in the runtime matrix with a 0.94 GB artifact and bounded memory use.
Compared with the open-model rows on Omi's standing 30-system board, MLX q8 has the lowest observed WER and the second-lowest observed M-WER. These are positions in this benchmark draw, not a universal ranking.
The previous model-card figures were produced by an older runtime/scorer path. The numbers above supersede them as runtime results; the q8 weights did not change.
Compatibility
This is not a drop-in parakeet-mlx checkpoint. Omi Med STT v1 includes a
medical adapter, and the supported Mac path is the omi-med-stt CLI.
Links
- Canonical model:
omi-health/omi-med-stt-v1 - Full MLX export:
omi-health/omi-med-stt-v1-mlx - CPU GGUF export:
omi-health/omi-med-stt-v1-gguf - Runtime CLI:
Omi-Health/omi-med-stt-runtime - Broader evaluation and product context: omi.health/research/omi-med-stt
Safety
Omi Med STT v1 is speech-to-text only. It is not a diagnostic, triage, prescribing, or clinical decision model, and it is not clinically validated. Transcripts must be reviewed before any clinical use.