Voxtral-4B-TTS-2603-TurboQuant-MLX-2bit

2-bit MLX weight-quantized build of mistralai/Voxtral-4B-TTS-2603 with a TurboQuant KV-cache profile. Extreme-compression TTS variant for memory-constrained Apple Silicon.

Overview

• Base: mistralai/Voxtral-4B-TTS-2603 — 4B multilingual TTS with zero-shot voice cloning
• Weight precision: 2-bit (group-wise)
• KV-cache profile: TurboQuant
• Approx. on-disk size: ~1.2 GB
• Runtime: MLX on Apple Silicon

Expect minor naturalness degradation vs 4-bit. Works best for a stable single-voice, single-language deployment. For multi-voice batches consider the RotorQuant 2-bit variant.

Quickstart

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("majentik/Voxtral-4B-TTS-2603-TurboQuant-MLX-2bit")

prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": [
        {"type": "audio", "path": "reference_voice.wav"},
        {"type": "text", "text": "Short prompt."},
    ]}],
    add_generation_prompt=True,
)
audio_tokens = generate(model, tokenizer, prompt=prompt, max_tokens=1024)

Model specs

Field	Value
Parameters	4B
Weight bits	2
Group size	32
Cache profile	TurboQuant
Languages	9
Voice cloning	Zero-shot
Size on disk	~1.2 GB
Target hardware	Apple Silicon (M1/M2/M3/M4)
License	Apache 2.0

RotorQuant vs TurboQuant

	TurboQuant	RotorQuant
Strategy	Per-head static calibration	Rotational online re-basis
Memory reduction	~3.5x on KV-cache	~4x on KV-cache
Best for	Single-voice sessions	Multi-voice / multi-language batches

See also

• majentik/Voxtral-4B-TTS-2603-RotorQuant-MLX-2bit
• majentik/Voxtral-4B-TTS-2603-TurboQuant-MLX-4bit
• majentik/Voxtral-4B-TTS-2603-TurboQuant-MLX-8bit
• majentik/Voxtral-4B-TTS-2603-TurboQuant — KV-cache-only bundle
• mistralai/Voxtral-4B-TTS-2603 — upstream base model