Sign in

Repository Index

111,821 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters

Filters

Clear all filters

745–768 of 872 · Most stars

Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.

Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.

  • calibration
  • cuda
  • cuda-graphs
  • decision-making

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.

Official Implementation of Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agents

  • continual-pretraining
  • embodied-agent
  • foundation-model
  • game-agent

📹 Open-source, self-hosted WebRTC 1-to-1 video calling for private real-time communication. Build secure browser-based consultations, coaching, support, telehealth, and other video call experiences with peer-to-peer communication and screen sharing.

SCENIC is an R package to infer Gene Regulatory Networks and cell types from single-cell RNA-seq data.

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.

  • ai
  • ai-interpretability
  • ai-safety
  • aisafety

An open-source columnar data format designed for fast & realtime analytic with big data.

  • indexr
  • columnar-storage
  • olap
  • datawarehouse

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