@no_stp_on_snek: wow look at the gains on metal!!!
Summary
The Qwen MLX Challenge is a competition for benchmarking AI models on Apple Silicon, with official scores and local iteration encouraged during validation.
View Cached Full Text
Cached at: 08/17/26, 08:27 PM
wow look at the gains on metal!!! 👀👀 https://t.co/5djHHpYYMq
The Qwen MLX Challenge
Source: https://www.yukon.org/mlxfast official scores are paired Apple Silicon measurements; keep iterating locally while the validation queue works
Copyright © 2026Eigen Labs, Inc.
Similar Articles
Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon
Metal-Sci introduces a 10-task benchmark for optimizing scientific computing kernels on Apple Silicon, paired with an evolutionary search framework driven by large language models. The study evaluates models like Claude Opus 4.7, Gemini 3.1 Pro, and GPT 5.5, demonstrating significant speedups while using out-of-distribution testing to catch silent performance regressions.
@neural_avb: I am working on porting SAM models and harness into Apple silicon. Already seeing 1.25x inference speed increase on mlx…
Porting SAM 2.1 models to Apple silicon with MLX, achieving 1.25x inference speed increase on the small model, with quantized versions planned.
Qwen3.8-27B is now up to ~3× faster on Apple Silicon with mlx-dspark
mlx-dspark v0.10.0 adds support for Qwen3.8-27B on Apple Silicon, providing up to 3x faster inference through speculative decoding with lossless verification.
@no_stp_on_snek: https://x.com/no_stp_on_snek/status/2052833502475833384
An open-source stack using Qwen2.5-32B-Instruct with longctx and vllm-turboquant on a single AMD MI300X achieves competitive results (0.601-0.688) versus SubQ's closed model (0.659) on the MRCR v2 1M-context benchmark, demonstrating open-weights approaches are within striking distance.
I built mlx-Chronos — a community benchmark leaderboard for local LLM engines on Apple Silicon (oMLX, Rapid-MLX, mlx-lm, Ollama)
A CS student built mlx-Chronos, an open-source CLI tool that standardizes benchmarking of MLX inference engines on Apple Silicon by measuring TTFT, throughput, memory usage, and thermal state, with a community leaderboard for sharing results.