tokenspeed

TokenSpeed is a speed-of-light LLM inference engine.

★ 2,473 stars, verified 2026-10-16Category: Local LLMs & InferenceGitHub repository ↗

TokenSpeed is a speed-of-light LLM inference engine.

Run open LLMs on your own machine — no API bills, no data leaving your device.

Stack & tags

b200b300blackwelldeepseekgb200gb300glmgpt-oss

★ 181,956

Run LLMs locally with one command: `ollama run llama3`. Mac/Win/Linux supported.

★ 129,965

C/C++ LLM inference engine, birthplace of the GGUF format; powers Ollama under the hood

Local LLMs & InferenceGitHub ↗