Local LLM Index / local
← All tools
The Local LLM Index / Inference Engines / #43

youssofal/MTPLX

by youssofal · Inference Engines · updated today

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

70
momentum
2,344
stars
174
forks
#43
rank
anthropic-compatibleapple-siliconclaude-codeflash-nextinference-enginellm-inferencelocal-ailocal-llmmacosmetalmlxmtp
View on GitHub →

More in Inference Engines

Inference Engines#11
local-deep-research
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cp
Inference Engines#15
khoj
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom a
Inference Engines#20
lemonade
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from t
Inference Engines#32
LLamaSharp
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.