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)
Refine

Source:

Engine
Model
Quant
Storage requirement
Feature tags

Reset

Filters: moriyasujapan clear all

1 recipe · page 1 of 1

Community builds

Ampere (1)

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

Qwen3.8-Flash-Next W4A16 2x CMP 170HX TP2+EP MTP4 FP8 PLE 92GB Host

by moriyasujapan (recipe, local FP8 PLE conversion, measurements)↗, alesha-pro/qwen38-flash-next-4x3090 (PLE offload overlays + manifest tooling, pinned not vendored)↗, VnimanieAI (base W4A16 quantization)↗, trohrbaugh (heretic-2 refusals-removed checkpoint) + densohax (its W4A16 quantization)↗, loktar00/qwen38-flash-next-vllm-3090-recipe (starting settings + MTP findings)↗, RadixArk/Qwen3.8-Flash-Next-NVFP4 (FP8 PLE layout reproduced bit-identically)↗ · listed by localai-recipes

vLLM recipe for plain Qwen3.8-Flash-Next W4A16 on two STOCK CMP 170HX (Gen2 x16, no P2P) on a LOW-RAM 92 GiB host. Differentiator: the 95.4 GiB BF16 PLE table is converted LOCALLY

Qwen3.8-Flash-Next vllm NVIDIA CMP 170HX 64GB ×2 (Ampere) 101.3 tok/s decode · 2839 tok/s prefill