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)CMP 170HX 64GB (Ampere): Any6 cards (1)4 cards (10)3 cards (2)2 cards (15)1 card (3)Radeon AI Pro R9700 32GB (AMD): Any2 cards (1)1 card (1)RTX 5090 32GB (Blackwell): Any2 cards (1)1 card (1)
Refine

Source:

Engine
Model
Quant
Storage requirement
Feature tags

Reset

Filters: rtx-5090-x2 170hx-x6 radeon-ai-pro-r9700 code clear all

3 recipes · 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.

GLM-5.3-Flash EXL3 2.05bpw on 2x RTX 5090 - TabbyAPI hot-expert swaps, 262K ctx, vision

by adrienbrault (recipe, five patch overlays, measurements)↗, zai-org (GLM-5.3-Flash)↗, turboderp (EXL3 2.05bpw quantisation; ExLlamaV3 + CPU MoE offload)↗, theroyallab (TabbyAPI)↗, adrienbrault/qwen3.8-flash-next-2x-rtx5090 (base image: ExLlamaV3 dev 5783a93 patch stack + TabbyAPI 53da7919)↗ · listed by localai-recipes

GLM-5.3-Flash (321B MoE, ~18B active) turboderp EXL3 2.05bpw on two RTX 5090 + 64 GB DDR5: TabbyAPI on ExLlamaV3 with CPU-offloaded routed experts (96/layer GPU0 layers 3-22+MTP, 1

GLM-5.3-Flash exllamav3 NVIDIA RTX 5090 32GB ×2 (Blackwell) 62.9 tok/s decode · 2023 tok/s prefill

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

AMD (1)

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

Qwen3.8-27B MXFP4 DFlash2 1x Radeon AI PRO R9700 WSL2 radiance

by mike2153 (recipe, WSL2 installer, benchmarks)↗, StillDeadcode (vllm-radiance image + libr4d kernels)↗, ggz14 (radiance-vllm-mxfp4 fork)↗, magiccodingman (radiance RDNA4 kernel lineage), Inco AI / tcclaviger (DFlash2 FP8 drafter requant)↗, AMD (official Qwen3.8-27B Quark AWQ-MXFP4 checkpoint + ROCm librocdxg)↗ · listed by localai-recipes

Qwen3.8-27B on a single AMD Radeon AI PRO R9700 (RDNA4 gfx1201, 32 GB) under Windows 11 + WSL2: vLLM radiance 0.9.3 fork pinned by image digest with AMD's official Quark AWQ-MXFP4

Qwen3.8-27B vllm AMD Radeon AI Pro R9700 32GB ×1 115 tok/s decode · 2762 tok/s prefill