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) (32)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 4090 24GB (Ada Lovelace) (1)CMP 170HX 64GB (Ampere): Any6 cards (1)4 cards (10)3 cards (3)2 cards (15)1 card (3)DGX Spark 128GB (Blackwell): Any4 cards (3)3 cards (1)2 cards (3)1 card (10)RTX 5090 32GB (Blackwell): Any2 cards (1)1 card (1)RTX 4090 24GB (Ada Lovelace): Any1 card (1)
Refine

Source:

Engine
Model
Quant
Storage requirement
Feature tags

Reset

Filters: dgx-spark-x2 170hx-x6 rtx-4090 rtx-5090 clear all

6 recipes · page 1 of 1

Community builds

Blackwell (4)

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

DeepSeek-V4.1-Flash-1017 streaming NVMe stack on 1x RTX 5090 (fronteagle739)

by fronteagle739 - recipe, streaming stack and measurements↗, llama.cpp / ggml (MIT)↗, antirez/ds4 (MIT)↗, IngeniousIdiocy/ds4-v41-m3ultra (MIT)↗, DeepSeek - DeepSeek-V4.1-Flash-1017 base model↗ · listed by localai-recipes

Streams a 483 GiB DeepSeek-V4.1-Flash-1017 pack from NVMe straight into one 32 GB RTX 5090, so a frontier-size MoE runs on a desktop with 32 GB of VRAM and 32 GB of system RAM. Win

DeepSeek-V4.1-Flash-1017 llama.cpp NVIDIA RTX 5090 32GB ×1 (Blackwell) 17.8 tok/s decode · 3356 tok/s prefill
Qwen3.8-Flash-Next Uncensored NVFP4 2x DGX Spark SGLang TP2 ROCE

by ttlogan↗, PixelML/MiaAI (SM121 QSA fallback + token-0 guard patches, MIT), jpezzulli (OrcaRouter uncensored ModelOpt NVFP4 + FP8 PLE repack)↗ · listed by localai-recipes

Recipe by ttlogan. Production 2-node GB10 (ASUS GX10 / DGX Spark) cluster serve of jpezzulli/OrcaRouter-Qwen3.8-Flash-Next-Uncensored-ModelOpt-NVFP4 (OrcaRouter uncensored weights

Qwen3.8-Flash-Next sglang NVIDIA DGX Spark 128GB ×2 (Blackwell) 40.3 tok/s decode · 2936.7 tok/s prefill

Ada Lovelace (1)

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

Qwen3.8-Flash-Next IQ3_S + MTP on 1x RTX 4090 — llama.cpp + tandem.cpp MoE expert cache (ewhacc)

by ewhacc - recipe, patch set and measurements↗, llama.cpp / ggml (MIT)↗, MoE expert-split rule adapted from Strata (Niko1221)↗ · listed by localai-recipes

MoE expert-cache offload for llama.cpp via the tandem.cpp patch set: hot experts stay in a GPU expert cache, missed experts are split between CPU compute and an upload into the cac

Qwen3.8-Flash-Next llama.cpp NVIDIA RTX 4090 24GB ×1 (Ada Lovelace) 48 tok/s decode

Ampere (1)

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

DeepSeek-V4.1-Flash SM80 DeepInfer kernel port 6x CMP 170HX DSpark K5

by HalfVulpes (Deepinfer-SM80 port + measurements)↗, DeepSeek-AI (DeepInfer engine architecture + DeepSeek-V4.1-Flash checkpoint)↗, vLLM project (V1 engine + TPxPP runtime)↗, TileLang + OpenAI Triton (SM80 kernel synthesis)↗, FlashInfer + IST-DASLab Marlin (sparse-MLA + MXFP4/W4A16 Ampere GEMM primitives)↗ · listed by localai-recipes

DeepSeek-V4.1-Flash served on six 64 GB SM80 GPUs (GA100 die, owner-classified 170HX) with HalfVulpes' Deepinfer-SM80 patch set: a 30-file vLLM V1 overlay porting DeepSeek's DeepIn

DeepSeek-V4.1-Flash TP+PP vllm +2