m96-chan/MioTTS-0.6B-q8-webgpu

MioTTS-0.6B, int8 for the browser

Aratako/MioTTS-0.6B quantized to per-row int8 so it can run in a web browser on WebGPU, as part of voxshot.

This is a repackaging, not a new model. Every weight comes from the Apache-2.0 checkpoint above; nothing was trained, fine-tuned or distilled. Please cite and credit the original.

Source checkpoint	1,217,825,224 B (bf16)
This one	611,153,856 B (int8 + f32 scales)

Why this exists

A browser cannot afford the bf16 checkpoint, and the op library this runs on (web-xpu-ops) has exactly one quantized kernel: a fused W8A32 GEMV over per-row absmax int8. So that is the format. There is no f16 path — no shader-f16 kernels exist upstream.

Files

file	bytes	contents
manifest.json	68,159	per-tensor offsets, shapes, config, provenance
weights.codes.bin	608,829,440	int8 codes, one byte each, tensors concatenated
weights.scales.bin	2,034,176	f32, one scale per output row
weights.norms.bin	290,816	f32 norm vectors, unquantized

manifest.json is the index: every tensor entry carries rows, cols and a byte offset into the file it lives in. Nothing else is needed to read these.

The quantization

Per-row absmax symmetric int8. For each output row, scale = max|w| / 127 and code = round(w / scale) clamped to [-127, 127]; an all-zero row gets scale = 1. Rounding is half-up, matched bit-for-bit against the consumer's own quantize op on real rows of this checkpoint.

Quantized: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj per layer, and embed_tokens once — the embeddings are tied, so that one matrix serves as both the lookup table and the output projection. Left in f32: the layer norms and the per-head q/k-norm gains, 291 KB in total, where quantization would buy nothing and cost accuracy.

What it costs, measured

Against the f32 original, stage by stage:

• element error at the theoretical bound, ~`scale/2` ≈ 0.0039 of each row's peak
• prompt logits within 4.8e-2 peak-relative (Japanese) and 1.2e-2 (English), with the argmax unchanged at the prompt boundary in both
• greedy generation diverges from f32 at step 6 on a Japanese test sentence: an adjacent-codebook near-tie flips, and the trajectory then differs while remaining well-formed — 87 speech tokens and a clean EOS against f32's 83.

That last point matters if you plan to compare outputs: int8 does not reproduce the f32 token sequence, and it is not supposed to. Compare against an int8 reference, or compare the audio.

RoPE channels are permuted

q_proj and k_proj rows, and the q_norm / k_norm gains, are relabeled from Hugging Face's rotate-half pairing (j, j+64) to the adjacent-pair pairing (2i, 2i+1) that the consumer's RoPE kernel implements. Per head: j → 2j for j < 64, else j → 2(j-64)+1.

manifest.json records this as "ropePermuted": true. The unpermuted gains are also stored, as qNormRaw / kNormRaw, so the original order is recoverable.

If you feed these weights to a stock Hugging Face implementation without undoing the permutation, you will get noise. They are shaped for one consumer.

Provenance

Produced by spike/miotts/convert_weights.py from:

Aratako/MioTTS-0.6B  model.safetensors
  1,217,825,224 bytes
  sha256 d0f85e5d9799c1589d7ba7c1c7830a7e2b6e4424ed07da2f76a56bc2ed7dc449

The converter re-hashes that file and aborts on a mismatch, and manifest.json records the digest, so these weights and the checkpoint they came from cannot drift apart unnoticed.

Architecture, for reference

Qwen3, 28 layers, hidden 1024, 16 query heads / 8 KV heads, head dim 128, FFN 3072 SwiGLU, RMSNorm eps 1e-6, RoPE theta 1e6, tied embeddings, vocab 164,480. Speech tokens are <|s_n|> = id 151669 + n for n in 0..12799, which index Aratako/MioCodec-25Hz-24kHz at 25 tokens per second.

License and attribution

Apache-2.0, inherited from the source checkpoint.

• Model: Aratako/MioTTS-0.6B by Chihiro Arata
• Codec it pairs with: Aratako/MioCodec-25Hz-24kHz (MIT)

@misc{miotts,
  author = {Chihiro Arata},
  title = {MioTTS: Lightweight and Fast LLM-based Text-to-Speech},
  year = {2026},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\url{https://huggingface.co/collections/Aratako/miotts}}
}