capy-flash

Qwen3.8-Flash-Next (MoE, NVFP4) and Qwen3.8-27B on two 16 GB consumer GPUs: two-GPU tensor parallel, experts offloaded to CPU. Formerly ninfer-tp2.

43 8

last commit 2026-10-16

About

Qwen3.8-Flash-Next (MoE, NVFP4) and Qwen3.8-27B on two 16 GB consumer GPUs: two-GPU tensor parallel, experts offloaded to CPU. Formerly ninfer-tp2.

No features listed.

Comments Theme

Platforms

Hosting

Self-hosted

Install

Docker

Build from source

Keywords

slug: capy-flash