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)CMP 170HX 64GB (Ampere): Any6 cards (1)4 cards (10)3 cards (3)2 cards (16)1 card (3)RTX PRO 6000 Blackwell 96GB: Any4 cards (5)3 cards (1)2 cards (6)1 card (7)RTX 4090 24GB (Ada Lovelace): Any1 card (1)
Refine

Source:

Engine
Model
Quant
Storage requirement
Feature tags

Reset

Filters: rtx-pro-6000-blackwell-x2 170hx rtx-4090 170hx-x6 vision clear all

3 recipes (1 beta hidden) · page 1 of 1

Community builds

Blackwell (2)

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

DeepSeek-V4.1-Flash-1017 EXL3 3bpw 2x RTX PRO 6000 Engram on SSD

by yoloyash (recipe author: SSD Engram overlay, native row gather, SSD plans, measurements, MIT)↗, diffbot (pack, image, kernels, serve.sh, model-card numbers: diffbot/DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000), deepseek-ai/DeepSeek-V4.1-Flash-1017 - upstream weights · listed by localai-recipes

DeepSeek-V4.1-Flash-1017 (diffbot's EXL3 3bpw pack) on 2x RTX PRO 6000 96 GB with only 128 GB of host RAM instead of the ~256 GB diffbot's own recipe pins. No fork, no rebuild: fiv

DeepSeek-V4.1-Flash-1017 vllm NVIDIA RTX PRO 6000 Blackwell 96GB ×2 167.3 tok/s decode · 7360 tok/s prefill

Ampere (1)

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

Qwen3.8-Flash-Next 3bpw FP8-PLE 1x CMP 170HX DFlash2 RecoverSSM

by ElectroHobo↗, Morrowmake (vllm-cmp170hx engine + image + Qwen EXL3 recipe scripts this descends from, MIT)↗, klee100 (3 bpw AutoRound checkpoint with its MTP head, made for a 64 GiB card; not involved in this recipe)↗, halt95 (W4A16-Merlin checkpoint whose FP8 n-gram table this recipe serves; not involved in this recipe)↗, inco.ai (DFlash2 drafter, Apache-2.0)↗, Intel (AutoRound quantisation) + RadixArk (FP8 n-gram table quantisation)↗, Qwen (Qwen3.8-Flash-Next base model, Qwen Community License 1.0)↗, MiaAI-Lab (benchmark protocol + category prompts, used as data)↗ · listed by localai-recipes

Qwen3.8-Flash-Next (125B MoE) 3 bpw AutoRound experts on ONE CMP 170HX card with the full 262,144-token context: 197.8/296.4/135.5 tok/s one user (structured/code/prose), 371 tok/s

Qwen3.8-Flash-Next TP vllm +2