Ross ROSS = Recommend OSS · open-source software intelligence for agents

youssofal/MTPLX

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter. observed · 2026-08-28

github.com/youssofal/MTPLX · homepage · Python · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

81/100

  • Activity 99
  • Release rhythm 99
  • Longevity 8

Flags: young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0.0
  • age_days: 124
  • days_rel: 8
  • days_push: 8
  • n_releases_24m: 43

Full methodology

Adoption not part of the score

1698 stars · 127 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

MTPLX is a native macOS app and CLI that runs local LLMs on Apple Silicon roughly twice as fast using native multi-token prediction (MTP) speculative decoding, with exact rejection sampling that preserves output distribution. It ships an OpenAI/Anthropic-compatible local server, a built-in chat UI, and a model forge that converts Hugging Face models to MLX.

Use cases

  • run local llms faster on my mac
  • serve an openai-compatible local model endpoint on apple silicon
  • speed up qwen inference with speculative decoding
  • chat with local models offline on m-series macs
  • convert a hugging face model to mlx and measure speedup
  • power coding agents like opencode with a local model
  • run llm inference without an external draft model

When to choose

  • you have an Apple Silicon Mac (M1+, macOS 14+) and want faster local LLM inference with identical output
  • you use MTP-capable models like Qwen 3.5/3.6/3.8 and want native speculative decoding without a second draft model
  • you need an OpenAI- or Anthropic-compatible local server for coding agents and tools
  • you want a one-click Mac app experience including model download and hardware-based recommendations

When to avoid

  • you run on Linux, Windows, or non-Apple hardware
  • you need models without MTP heads or broad model-family support
  • you need multi-GPU or datacenter-scale serving rather than single-machine local inference
  • you require a runtime with a long track record or large maintainer team

Facets

application · maturity active

llm-inference cli chatbot large-language-models machine-learning self-hosted developer-tools cli speculative-decoding multi-token-prediction mlx apple-silicon openai-compatible anthropic-compatible local-llm qwen metal inference-engine macos apple-ecosystem

5 sources

Member repositories

RepositoryRoleHealth v2
youssofal/MTPLXmain81

For agents

markdown · JSON · MCP: product_card(name="youssofal/MTPLX")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem