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)CMP 170HX 64GB (Ampere): Any6 cards (1)4 cards (10)3 cards (3)2 cards (15)1 card (3)RTX PRO 6000 Blackwell 96GB: Any4 cards (5)3 cards (1)2 cards (5)1 card (7)Radeon AI Pro R9700 32GB (AMD): Any2 cards (1)1 card (1)
Refine

Source:

Engine
Model
Quant
Storage requirement
Feature tags

Reset

Filters: rtx-pro-6000-blackwell-x3 170hx-x3 radeon-ai-pro-r9700 clear all

5 recipes · page 1 of 1

Ampere (1)

Community builds

Blackwell (1)

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

DeepSeek-V4.1-Flash-1017 Kraken TP3 3x RTX PRO 6000 Blackwell

by BoxTops4Coochie (recipe, TP3 port, measurements)↗, infernix - ds41f-tp3 expert-parking design on karmic-kraken↗, Local Inference Lab - vLLM karmic-kraken fork + FlashInfer b12x kernels↗, DeepSeek - DeepSeek-V4.1-Flash-1017 base model (MIT)↗ · listed by localai-recipes

DeepSeek-V4.1-Flash-1017 TP3 on three 96 GB RTX PRO 6000 Blackwell cards, full 1M context, DeepSeek's original weights (FP8 dense + MXFP4 experts, nothing requantized). Expert laye

DeepSeek-V4.1-Flash-1017 TP vllm +2

Ampere (2)

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

Qwen3.8-Flash-Next Uncensored AWQ-g32 on 3x CMP 170HX — PP3, 1M ctx, NVMe PLE, MTP-4 (givisok)

by recipe, tuning notes and measurements by givisok↗, base stack and vllm-sm80 fork by clee↗, AWQ-g32 checkpoint by leoncca↗, uncensored base by orcarouter↗, cudagraph capture-size idea from mannydelrio↗, vLLM (Apache-2.0)↗ · listed by localai-recipes

MTP-4 production recipe for Qwen3.8-Flash-Next-Uncensored (leoncca AWQ-g32) on 3x CMP 170HX (SM80 cards unlocked to 64 GiB): PP3 partition 17,17,14 (no GPU P2P on this pairing; the

Qwen3.8-Flash-Next PP vllm +2
Qwen3.8-Flash-Next W4A16 3x CMP 170HX PP3 NVMe PLE fp8 KV 1M (clee)

by clee (recipe, fork patches, bench + needle harness)↗, clee (vllm-sm80 fork: units-fix, fp8-kv-sm80, ple-pp3, ple-nvme-staged)↗, Kai / 2Wild (Qwen38-Flash-Next-4x3090 — staged-PLE architecture inspiration)↗, Intel (INT4 W4A16 AutoRound quant)↗, froggeric (bugfixed Qwen3.8 chat templates)↗ · listed by localai-recipes

Working PP3 recipe for Qwen3.8-Flash-Next (Qwen4Exp 180B-A6B MoE, Intel INT4 W4A16 AutoRound) on 3x CMP 170HX (SM80, unlocked 64 GiB each): the 95.4 GiB BF16 PLE n-gram table strea

Qwen3.8-Flash-Next vllm NVIDIA CMP 170HX 64GB ×3 (Ampere) 59.8 tok/s decode · 4690 tok/s prefill

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