Qwen 3.8 27B running locally on an RTX 5090 beats Opus 4.8 in personal benchmarks at up to 200 tokens…
Qwen 3.8 27B running locally on an RTX 5090 beats Opus 4.8 in personal benchmarks at up to 200 tokens per second with no internet, subscription or API required and is now powering a Hermes agent working 24/7 for free.
Here is my first local Qwen 3.8 Flash Next result.
I am disappointed to learn that the current releases that can run on my Mac do not have vision so my images ended up getting tossed for SVG's which I almost never like. Using this quant: 25.3
Wow! This is the best looking NYC Brick Town yet.
Qwen 3.8-Flash-Next running on ONE DGX Spark!!! One pass only. No redos or refinements… Hermes Agent is my harness. Local AI at its finest.
You have reached the end of the archive
All of qwen38