apple-silicon-llm-bench/results/complete_results.html at main · AlexHiesch/apple-silicon-llm-bench

Systematic LLM inference benchmark for Apple Silicon: 8 backends, 7 models, 791 measurements - AlexHiesch/apple-silicon-llm-bench

Geek Lite on Twitter / X

在 Apple Silicon Mac 上本地运行 LLM 推理服务，提供比 Ollama 和 llama.cpp 更快的 OpenAI 兼容 API，同时原生支持工具调用和提示缓存。https://t.co/IXet9GW7x0Rapid-MLX 用 Apple 自家的 MLX 框架做推理，搭了个 FastAPI 服务跑 OpenAI 兼容 API。在 Apple Silicon 上比 Ollama 快 2-4 倍，靠… pic.twitter.com/d9QUbAWJSZ— Geek Lite (@QingQ77) May 3, 2026

alphaXiv

Discuss, discover, and read arXiv papers.

FOSDEM 2026 - FOSDEM 2026 Call for Participation

Proposals for developer rooms and main track talks for FOSDEM 2026 can now be submitted!

Lei Yang on Twitter / X

Got burned by an Apple ICLR paper — it was withdrawn after my Public Comment.So here’s what happened. Earlier this month, a colleague shared an Apple paper on arXiv with me — it was also under review for ICLR 2026.The benchmark they proposed was perfectly aligned with a… pic.twitter.com/ON782SFNjI— Lei Yang (@diyerxx) November 27, 2025

Artur Chakhvadze on Twitter / X

We are releasing our first quantized checkpoints for the Qwen3.5 series of models, co-designed jointly with our inference engine to achieve maximum possible performance on Apple hardwareStarting from 0.8B, 2B and 4B modelshttps://t.co/2R8BdhAfzv— Artur Chakhvadze (@norpadon) June 8, 2026

The 2026 AI Index Report | Stanford HAI

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Cua on Twitter / X

1/ Today, as part of our broader research into Apple Silicon virtualization, we're releasing a process-scoped Metal capability layer for macOS VMs. On one M1 Ultra, prompt / generation:TinyLlama: 11.08× / 16.36×Gemma 4 12B: 7.20× / 14.54×Muse Glimmer 30B: 7.55× / 8.87× pic.twitter.com/6UwxgoDowT— Cua (@trycua) August 11, 2026

vllm-project/vllm-metal

Community maintained hardware plugin for vLLM on Apple Silicon

Introducing Laguna S 2.1

Today we’re releasing Laguna S 2.1, a significant step forward in our development of models that pursue longer horizon work and make effective use of reasoning.

AI Engineer's 2025 | Unsloth Documentation

Slides to our AI Engineer's Worlds Fair 2025 Workshop.

Models on-device | Ai2

Ai2, a non-profit research institute founded by Paul Allen, is committed to breakthrough AI to solve the world’s biggest problems.