MacBook Pro M5 Max

mentions 3 type Person feed RSS

// recent coverage 3 mentions

15:31

2026-09-23

discuss.huggingface.co

large-language-models

Trying to improve output speed with MLX models on LM Studio

An LM Studio user running version 0.4.25+1 on a MacBook Pro M5 Max with 128 GB of RAM reports getting 15-17 tokens per second from the mlx-community/Qwen3.8-27B-8bit model and cannot enable speculativ…

14:42

2026-08-23

gladlabs.io

artificial-intelligence

Qwen 3.8 27B Needs 22,000 Tokens to Draw a Pelican

Alibaba's Qwen 3.8 27B open-weight vision model, released under Apache 2.0, takes 21 minutes and 22,276 reasoning tokens to draw a pelican riding a bicycle as an SVG, according to Simon Willison's tes…

00:00

2026-08-01

zackproser.com

artificial-intelligence

The Price Floor

DeepSeek's V4 Flash 0731, a 284-billion-parameter open-weight mixture-of-experts model released under the MIT license on July 31, runs at 107 tokens per second on DeepSeek's API and 267 on the fastest…

// co-occurs with top 8 entities

Apple 2 Hugging Face 2 DeepSeek 1 V4 Flash 0731 1 NVIDIA 1 Alibaba 1 Qwen 3.8 27B 1 Simon Willison 1

// topics top 6 topics

large language models 3 artificial intelligence 2 ai tools 2 ai infrastructure 1 ai products 1 ai research 1