localairecipes launch configs for local inference

Working launch recipes for local LLM inference

Engine configs (vLLM, SGLang, llama.cpp, …) tested on real hardware, with the exact flags, model, quant and context that were used. Copy one, run it, or hand it to your agent. Search or refine below; every recipe on the site is listed here.

Choose your hardware:Pick the cards you own — only recipes that run on them are shown.
CMP 170HX 64GB (Ampere) (31)RTX PRO 6000 Blackwell 96GB (18)DGX Spark 128GB (Blackwell) (14)✓ RTX 3090 24GB (Ampere) (7)Radeon AI Pro R9700 32GB (AMD) (2)RTX 5090 32GB (Blackwell) (2)DGX Station (GB300) 288GB (Blackwell) (1)RTX 3090 24GB (Ampere): Any4 cards (2)2 cards (4)1 card (3)
Refine

Source:

Engine
Model
Quant
Storage requirement
Feature tags

Reset

Filters: qwen3-8-flash-next rtx-3090-x2 rtx-3090 clear all

2 recipes · page 1 of 1

Community builds

Ampere (2)

Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.

Qwen3.8-Flash-Next W4A16-FP8PLE on 2x RTX 3090 — TP2, expert-offload, MTP3 (DominikBucko)

by DominikBucko↗, albucino (checkpoint)↗, Intel AutoRound (W4A16 target)↗, RadixArk (FP8 PLE table)↗ · listed by localai-recipes

Two-card RTX 3090 recipe for Qwen3.8-Flash-Next (125B MoE) in the albucino W4A16-FP8PLE build (Intel AutoRound INT4 backbone + FP8 PLE table + INT4 MTP draft, checkpoint @ ef55414)

Qwen3.8-Flash-Next vllm NVIDIA RTX 3090 24GB ×2 (Ampere) 103.1 tok/s decode · 2865 tok/s prefill