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)DGX Station (GB300) 288GB (Blackwell) (1)RTX 5090 32GB (Blackwell) (1)RTX PRO 6000 Blackwell 96GB: Any4 cards (5)3 cards (1)2 cards (5)1 card (7)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-pro-6000-blackwell rtx-3090 clear all

4 recipes (1 beta hidden) · page 1 of 1

Blackwell (1)

Community builds

Blackwell (2)

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

Qwen3.8-Flash-Next NVFP4 RTX PRO 6000 Blackwell SGLang NVMe PLE

by yepapa-nest↗, jzinno (NVMe PLE streaming PR #36567 source tree)↗, sgl-project (SGLang upstream + PRs 36556/36749/36750)↗ · listed by localai-recipes

Single-card RTX PRO 6000 Blackwell (SM120, 96GB) recipe for Qwen3.8-Flash-Next on SGLang: the 51B N-gram PLE table is read straight off NVMe with io_uring as tokens need it (measur

Qwen3.8-Flash-Next sglang NVIDIA RTX PRO 6000 Blackwell 96GB ×1 180.9 tok/s decode · 9990 tok/s prefill

Ampere (1)

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