Local LLM Index / local
← All tools
The Local LLM Index / Inference Engines / #44

youssofal/MTPLX

by youssofal · Inference Engines · updated 1d ago

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

70
momentum
2,657
stars
210
forks
#44
rank
anthropic-compatibleapple-siliconclaude-codeflash-nextinference-enginellm-inferencelocal-ailocal-llmmacosmetalmlxmtp
View on GitHub →

More in Inference Engines

Inference Engines#12
local-deep-research
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cp
Inference Engines#19
lemonade
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from t
Inference Engines#27
Rapid-MLX
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference se
Inference Engines#30
LLamaSharp
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.