Flash-Next on two RTX 3090s: 111 tok/s decode

DominikBuckoAug 30108 stars

Dual-3090 build with 128GB RAM reporting about 4,200 tok/s prefill and 111 tok/s decode on long prompts.

Open on GitHub

Preview of Flash-Next on two RTX 3090s: 111 tok/s decode

Launch: Qwen3.8-Flash-Next
Use case: Gaming gpu
Format: Repo
Source: github.com

DominikBucko

See all

sergqwer

@sergqwer · Sep 29

Adds NVIDIA's NVFP4 quantisation to Strata so a single 12GB+ RTX 20 to 50-series card can host the MoE.

Niko1221

@Niko1221 · Sep 24

Open-source inference engine with an OpenAI/Anthropic-style local API that fits the 125B MoE onto a 12GB consumer GPU plus system RAM. The project behind the model's local-running surge.

MiaAI-Lab

@MiaAI-Lab · Sep 4

Step-by-step recipe to squeeze the 125B model onto one DGX Spark instead of two, with config and measured throughput.

peonist-ai

@peonist-ai · Aug 26

Container-based server tuned for the gfx1151 Strix Halo APU, aimed at squeezing maximum tokens per second from the 125B model on a mini-PC.

Open on GitHub

Flash-Next on two RTX 3090s: 111 tok/s decode

More built with Qwen3.8-Flash-Next