Sign in

Repository Index

111,085 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters (1)

Filters

Clear all filters

73–96 of 100 · Most stars

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.

jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.

Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.

llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.

  • ampere
  • consumer-gpu
  • cuda
  • ggml

SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run text, image, video and audio models with llama.cpp, vLLM, Diffusers and PyTorch.

  • ascend
  • audio
  • audio-generation
  • diffusers

C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer

MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.