qwen

qwen-scribe

Python

73

Private, local transcription and system-wide dictation for Apple Silicon.

MTPLX

Python

90

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

apex-inference-chip

Python

68

An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.

unsloth

Python

95

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

ollama

Go

95

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

tokenspeed

Python

90

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

lora-speedrun

Python

73

Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.

tau-0-vla

Python

82

This repo is the official implementation of "τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation".

deja-vu

Go

82

Search your past AI coding sessions — Claude Code, Codex, Cursor and 17 more. Indexes the session history they already wrote to disk, including months from before you installed it, and recalls it in any of them. No LLM, no embeddings, one local Go binary.