Local LLMs & Inference

turbo-fieldfare

by drumih · Swift

turbo-fieldfare is an open-source LLM inference tool written in Swift, released under the Apache-2.0 license. It has 6.9k GitHub stars and 460 forks, and was last updated in October 2026. Related topics: apple-silicon, gemma and gemma4.

“Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook”

— drumih, project description on GitHub

Details

CategoryLocal LLMs & Inference
GitHub stars6,944
Forks460
LanguageSwift
LicenseApache-2.0
Last updated
Ownerdrumih
Repositorydrumih/turbo-fieldfare

Tags

apple-silicongemmagemma4gemma4-26b-a4bgpgpullmllm-inferencelocal-ai

Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.

All Local LLMs & Inference

ai-infra-book

《深入理解 AI Infra:量化分析与系统设计》(李博杰 著)开源书稿:从硬件约束和模型架构出发,量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验

Local LLMs & Inference6.7k stars

flashinfer

FlashInfer: Kernel Library for LLM Serving

Local LLMs & Inference6.7k stars

kserve

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework…

Local LLMs & Inference6.1k stars

cactus

Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.

Local LLMs & Inference6.1k stars

shimmy

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No…

Local LLMs & Inference6k stars

lemonade

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and…

Local LLMs & Inference5.9k stars