CoolFace
Modelpublic

nRanzo/mlx-community-Qwythos-9B-v2-OptiQ-4bit-MTPLX

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face
0likes144downloads
Model Card

mlx-community-Qwythos-9B-v2-OptiQ-4bit-MTPLX

MTPLX-branded multi-token-prediction model optimized for Apple Silicon (MLX). Forged with MTPLX Forge from `mlx-community/Qwythos-9B-v2-OptiQ-4bit`.

Verification & Benchmarks

MetricResult
Speedup1.85× vs. autoregressive baseline
Throughput67.1 tok/s (Baseline: 36.3 tok/s)
Best DepthD2
Mean Acceptance Rate93% at D2
Hardware / OSApple M4 Pro · macOS 26.6.2
Sampler Configtemp=0.6, top_p=0.95, top_k=20
Refer to mtplx_runtime.json for the complete verification log.

Usage

MTPLX detects and initializes the model automatically once downloaded:

bash
# Pull model weights
mtplx pull nRanzo/mlx-community-Qwythos-9B-v2-OptiQ-4bit-MTPLX

# Launch interactive session
mtplx start chat

Project & Implementation

For benchmarks, speculative decoding pipelines, and testing methodology, visit the MLX-MTP Repository.

Attribution & License