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)DGX Spark 128GB (Blackwell): Any4 cards (3)3 cards (1)2 cards (3)1 card (10)RTX 3090 24GB (Ampere): Any4 cards (2)2 cards (4)1 card (3)
Refine

Source:

Engine
Model
Quant
Storage requirement
Feature tags

Reset

Filters: rtx-3090-x4 dgx-spark-x2 170hx chat clear all

8 recipes · page 1 of 1

Community builds

Blackwell (3)

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

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

Ampere (5)

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

Qwen3.8-Flash-Next W4A16-Merlin on 4x RTX 3090 — TP2xPP2+EP, MTP3, FP8 KV, 925K pool (halt95)

by halt95↗, Qwen (Qwen3.8-Flash-Next)↗, Intel AutoRound (INT4 experts)↗, RadixArk (FP8 PLE table)↗, DominikBucko (MTP INT4 packing recipe)↗, peakcrosser7 (Flash-Next vLLM branch)↗ · listed by localai-recipes

Four-card RTX 3090 recipe for Qwen3.8-Flash-Next (125B MoE) in halt95's W4A16-Merlin build (Intel AutoRound INT4 + FP8 PLE + MTP draft, @ 17284bf): TP2 x PP2 with expert parallel,

Qwen3.8-Flash-Next vllm NVIDIA RTX 3090 24GB ×4 (Ampere) 174.3 tok/s decode · 5236 tok/s prefill
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
Qwen3.8-27B INT8 MTP3 prefix-cache on 1x CMP 170HX Hynix

by ahnguyen17 (recipe, patches, probes, A/B benchmarks)↗, lued (Qwen3.8-27B-INT8-W8A16-MTP checkpoint)↗, vllm-project (vLLM upstream; #50021 GDN spec bounds, #45238 align-mode cache retention)↗ · listed by localai-recipes

Qwen3.8-27B at 65-67 tok/s decode (74 structured) with MTP k=3 speculative decoding AND prefix caching simultaneously on a single NVIDIA CMP 170HX 64GB (Hynix HBM2e, GA100/sm80), 2

Qwen3.8-27B vllm NVIDIA CMP 170HX 64GB ×1 (Ampere) 68.7 tok/s decode
Qwen3.8-Flash-Next 3bpw MTP on 1x CMP 170HX SSD PLE AIO (iIIusi0n)

by iIIusi0n (recipe, vLLM ple-ssd patch set, AIO helper, benchmark harness)↗, Qwen (official Qwen3.8-Flash-Next base, Qwen Community License 1.0)↗, klee100 (AutoRound 3bpw+MTP quantized checkpoints, official + uncensored)↗, OrcaRouter (Qwen3.8-Flash-Next-Uncensored BF16 abliterated fine-tune)↗, vLLM project (upstream vLLM @ a5a30471 the patch applies to)↗ · listed by localai-recipes

First single-CMP-170HX recipe for Qwen3.8-Flash-Next: the AutoRound 3bpw+MTP checkpoint on ONE 64 GiB SM80 GPU with the 95.37 GiB BF16 PLE table left ON the SSD — native Linux AIO

Qwen3.8-Flash-Next vllm NVIDIA CMP 170HX 64GB ×1 (Ampere) 111 tok/s decode · 2132 tok/s prefill