YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Qwen3.5-9B-MTPLX-FP16

MTPLX-branded multi-token-prediction model for Apple Silicon (MLX). Forged with MTPLX Forge from Qwen/Qwen3.5-9B.

Verification

  • Best depth: D2
  • Multiplier vs autoregressive baseline: 1.16脳
  • Verified on: Apple M1 Max
  • Sampler: temperature 0.6 路 top_p 0.95 路 top_k 20

See mtplx_runtime.json for the full verification record.

Usage

# MTPLX picks this model up automatically when downloaded:
mtplx pull Qwen-Qwen3.5-9B-MTPLX-FP16
mtplx start chat

License

See LICENSE.

Downloads last month
-
Safetensors
Model size
1B params
Tensor type
F16
U32
F32
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support