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) (33)RTX PRO 6000 Blackwell 96GB (19)DGX Spark 128GB (Blackwell) (16)RTX 3090 24GB (Ampere) (7)Radeon AI Pro R9700 32GB (AMD) (2)RTX 5090 32GB (Blackwell) (2)DGX Station (GB300) 288GB (Blackwell) (1)RTX 4090 24GB (Ada Lovelace) (1)
Refine

Source:

Engine
Model
Quant
Storage requirement
Feature tags

Reset

Filters: motif-3-nvfp4 clear all

1 recipe · page 1 of 1

Community builds

Blackwell (1)

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

Motif-3 NVFP4 314B 2x DGX Spark TP2 vLLM Fork FP8 Dense MTP

by sigjhl (recipe author, SM12x patch ladder, FP8 dense layer, measurements, Apache-2.0)↗, Motif Technologies (Motif-3-NVFP4 weights + vLLM fork base @ 4cd9eb41), eugr (spark-vllm nightly-20261016 - ring-aware NCCL 2.32.3), apache-tvm-ffi (xgrammar load_lib_module fix), NVIDIA (nvcr.io/nvidia/pytorch:26.02-py3 base image) · listed by localai-recipes

Recipe by sigjhl. Motif-Technologies/Motif-3-NVFP4 (314B total / 13.2B active MoE, 262k context, MTP) served on two NVIDIA DGX Spark (GB10, sm_121, 128 GB each) with tensor paralle

Motif-3-NVFP4 TP vllm +2