I gave Qwen 3.8 27B a reverse-engineering job I assumed needed a frontier model, and it finished in 30 minutes
- Qwen 3.8 27B was one of the most highly-anticipated open-weights releases that I've seen in a long time, and like many others, I immediately got to work testing it out and playing with it when it dropped.
- I'm running it on a single Lenovo ThinkStation PGX, the compact workstation built on Nvidia's GB10 Grace Blackwell chip, packing 128 GB of unified memory and 273 GB/s of bandwidth.
- Out of the box, it manages a fairly dull 15 to 30 tokens a second, but with an SGLang, NVFP4, and DFlash2 speculative-decoding setup that's become the standard recipe for this hardware, it can reach around 50 token
Unverified
- Qwen 3.8 27B was one of the most highly-anticipated open-weights releases that I've seen in a long time, and like many others, I immediately got to work testing it out and playing with it when it dropped.
- I'm running it on a single Lenovo ThinkStation PGX, the compact workstation built on Nvidia's GB10 Grace Blackwell chip, packing 128 GB of unified memory and 273 GB/s of bandwidth.
- Out of the box, it manages a fairly dull 15 to 30 tokens a second, but with an SGLang, NVFP4, and DFlash2 speculative-decoding setup that's become the standard recipe for this hardware, it can reach around 50 token
Sources: Xda-developers