The Big LLM Architecture Comparison

Kimi K2: 1 T‑Param DeepSeek‑Inspired MoE, Re‑engineered & Trained from Scratch

Still expecting Llama 4 Behemoth? Check Kimi K2.

MoE vs Dense vs Hybrid LLM Architectures

Train 600M MoE, Dense, Hybrid LLM Architectures.

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

Benchmarks | EXO

Transparent benchmarks for LLMs tested on real hardware. Coming soon.

On Kimi K3: Its Capabilities And Related Discontents

Kimi K3 is a very good model with excellent benchmarks.

leobeeson/llm_benchmarks

A collection of benchmarks and datasets for evaluating LLM.

Exploring LLMs with MLX and the Neural Accelerators in the M5 GPU

Mac with Apple silicon is increasingly popular among AI developers and researchers interested in using their Mac to experiment with the…

LLM Architecture Gallery

A gallery that collects architecture figures from The Big LLM Architecture Comparison and related articles, with fact sheets and links back to the original s...

vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Your Laptop Isn’t Ready for LLMs. That’s About to Change

The quest to run large AI models locally on an individual's machine are driving the biggest change in laptop architecture in decades.

Cerebras Launches World Fastest DeepSeek R1 Llama-70B Inference - Cerebras

Cerebras launches fastest DeepSeek

LLMs Can Now Write GPU Kernels That Beat torch.compile - Break AI Scaling Limits in 7 Days

We're now seeing multi-agent systems that take your PyTorch code and produce CUDA or Triton kernels with 2x to 14x speedups over torch.compile(mode='max-autotune-no-cudagraphs'). Not on toy benchmarks. On real models like Llama-3.1-8B, Whisper, and Stable Diffusion. Learn proven techniques to shift the scaling law intercept and achieve 10-50% performance gains.

LLM Leaderboard - Comparison of over 100 AI models from OpenAI, Google, DeepSeek & others

Comparison and ranking the performance of over 100 AI models (LLMs) across key metrics including intelligence, price, performance and speed (output speed - tokens per second & latency - TTFT), context window & others.

mzau/broke-cluster

A Poor Man's Apple Silicon LLM Cluster — tuned for MLX, scalable without shame.

Megakernel: Matching Apple Silicon Efficiency at 2x the Throughput on a RTX 3090

The first megakernel for hybrid DeltaNet/Attention LLMs. 413 tok/s at 1.87 tok/J on a 2020 RTX 3090, matching M5 Max efficiency at 1.8x throughput.