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: sm80 clear all

9 recipes · page 1 of 1

Ampere (1)

DeepSeek-V4.1-Flash-1017 Hybrid EXL3 TP4 4x CMP 170HX Morrowmake

by Morrowmake (recipe, engine fork, measurements)↗, LibertAI - EXL3 2.9-bpw routed-expert quantization↗, DeepSeek - DeepSeek-V4.1-Flash-1017 base model (MIT)↗, cmpunlocker (amoghmunikote) - P2P driver basis + minimal TRAP31 patch↗, MiaAI-Lab - decode benchmark protocol (used as data)↗, Marlin (IST-DASLab + Neural Magic contributors) - kernel basis↗ · listed by localai-recipes

DeepSeek-V4.1-Flash-1017 (748B MoE) on four CMP 170HX cards (sm_80): Morrowmake's release 1.0.0 recipe serves a hybrid checkpoint - routed experts from LibertAI's EXL3 2.9-bpw expo

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

Community builds

Ampere (8)

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

DeepSeek-V4.1-Flash-1017 Fidelity-First 4x CMP 170HX alanoo81

by alanoo81 (recipe, graft, measurements)↗, GNmac-lab (base recipe 1.2.0 @ 2ad5741ab1, MIT)↗, LibertAIDAI (EXL3 2.9bpw @ 0be63c33 / 3.5bpw @ 04a492fc)↗, Curtis White (hybrid layout + quantization_config.json)↗, vcruz305/vllm-exl3 (AGPL-3.0-only, inside the built image)↗ · listed by localai-recipes

DeepSeek-V4.1-Flash-1017 (748B MoE) on 4x CMP 170HX (sm_80, 64 GB each, PCIe Gen2 x16), TP4, as a fidelity-first variant of the GNmac-lab recipe 1.2.0 @ 2ad5741ab1 with four change

DeepSeek-V4.1-Flash-1017 TP vllm +2
DeepSeek-V4.1-Flash-1017 Engram-NVMe TP4/PP4 4x CMP 170HX

by GNmac-lab / greencandle (recipe, patches, measurements)↗, CurtisAccelerate - TP4 hybrid-checkpoint recipe + tensor-core EXL3 MoE port↗, zebgop-ops - dsv41reap-pp sm_80 sparse attention, PP shadow KV, DSpark V1, Engram row store↗, vcruz305 - vllm-exl3 (AGPL-3.0-only)↗, LibertAI - EXL3 2.9-bpw quantization (MIT)↗, DeepSeek - DeepSeek-V4.1-Flash-1017 base model (MIT)↗, kaka86mm - dsv41-flash-pp4-170hx (watched sibling)↗, Morrowmake - CMP 170HX recipe format, P2P work, tensor-core MoE kernels↗, Mia-AiLab - decode benchmark protocol + prompts (used as data)↗, FlashInfer - PCIe IPC all-reduce↗ · listed by localai-recipes

DeepSeek-V4.1-Flash-1017 (748B MoE) on four CMP 170HX cards power-capped at 180 W, with the model's 189 GiB Engram n-gram tables streamed from NVMe on demand. Recipe 1.2.0 (author

DeepSeek-V4.1-Flash-1017 TP+PP vllm +2
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
Qwen3.8-Flash-Next W4A16 2x CMP 170HX PP2 MTP5 PLE (AlexBrandes)

by AlexBrandes (recipe, fork, image, measurements)↗, AlexBrandes (vllm fork: PP + NVMe-mmapped PLE, Mamba PP state, draft lm_head, graph-safe PLE, bounded prefill)↗, polyuij42-del (community CMP 170HX W4A16 work the fork builds on)↗, nguyenthimy2022kg-alt (community SM80 170HX work the fork builds on)↗, MiaAI-Lab (sparkDash benchmark protocol @ 3e6d4ef)↗, Intel (INT4 W4A16 AutoRound quant)↗ · listed by localai-recipes

Recipe by AlexBrandes. Qwen3.8-Flash-Next (Intel/Qwen3.8-Flash-Next-W4A16-AutoRound @ 4c67bf68) on two NVIDIA CMP 170HX cards in PIPELINE parallel (PP2, layer split 26/22) with a v

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
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