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)RTX PRO 6000 Blackwell 96GB: Any4 cards (5)3 cards (1)2 cards (5)1 card (7)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-pro-6000-blackwell 170hx-x2 rtx-3090 vision clear all

10 recipes · page 1 of 1

Blackwell (1)

Community builds

Blackwell (1)

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

Ampere (8)

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

Qwen3.8-Flash-Next W4A16 2x CMP 170HX TP2 DFlash2 host-RAM PLE

by ElectroHobo↗, Morrowmake (vllm-cmp170hx engine + image + Qwen EXL3 recipe scripts this descends from, MIT)↗, halt95 (W4A16-Merlin checkpoint + companion 3090 engine; not involved in this recipe)↗, inco.ai (DFlash2 drafter, Apache-2.0)↗, Intel (AutoRound INT4 experts) + RadixArk (FP8 n-gram table) + DominikBucko (MTP-head packing)↗, 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) INT4-expert W4A16 on two CMP 170HX cards, full 262,144-token context: 241/350/198 tok/s one user (structured/code/prose), 495 tok/s editing code, 895/

Qwen3.8-Flash-Next TP vllm +2
Qwen3.8-Flash-Next-Uncensored AWQ W4A16 on 2x CMP 170HX — 8 slots, PP2, MTP5 + int4 draft head, PLE-from-SSD (mannydelrio)

by mannydelrio↗, AlexBrandes (W4A16 draft lm_head patch, quantizer)↗, cmpunlocker (amoghmunikote)↗, clee/vllm-sm80↗, wtdcode (vllm-backport)↗ · listed by mannydelrio1

Two-card Ampere pipeline recipe for Qwen3.8-Flash-Next-Uncensored (512-expert MoE), AWQ W4A16 g32: PP2 (CMP 170HX has no P2P), MTP 5-token drafting with an int4 draft-only lm_head,

Qwen3.8-Flash-Next vllm NVIDIA CMP 170HX 64GB ×2 (Ampere) 240.4 tok/s decode · 6964 tok/s prefill
GLM-5.3-Flash max effort on 2x CMP170HX EXL3 TP2 four slots

by alexvnesta (tensor-parallel fork: TP2, hybrid drafting, concurrent sessions, RAM tier, vision, NCCL backend)↗, Flun (original 2-card layer-split server + recipe this fork starts from)↗, turboderp (ExLlamaV3 engine + GLM-5.3-Flash-exl3 checkpoint + GLM-5.3 TP + vision tower support in engine)↗, incoai (GLM-5.3-Flash-DFlash2 BF16 drafter, CC BY-NC-ND 4.0)↗, 0xSero (k_hcfuse fused hyper-connection kernels, via Flun's repo)↗, Morrowmake (content-verified P2P check idea + benchmark prompt style)↗, bayley + arvkmr (fault probe idea + router-precision findings, vllm-170hx-glm5)↗, Z.ai (GLM-5.3-Flash base model)↗, msuiche (Weightless GLP-44 vector and specification)↗ · listed by alex.v.nesta

Four native active sequences on two 64 GiB CMP170HX cards; GLM-5.3-Flash EXL3 3.05bpw, TP2, with the Weightless GLP44 steering vector at alpha 2, FP16 recurrent state, Q8 GPU KV, D

GLM-5.3-Flash TP exllamav3 +2
GLM-5.3-Flash low effort on 2x CMP170HX EXL3 TP2 four slots

by alexvnesta (tensor-parallel fork: TP2, hybrid drafting, concurrent sessions, RAM tier, vision, NCCL backend)↗, Flun (original 2-card layer-split server + recipe this fork starts from)↗, turboderp (ExLlamaV3 engine + GLM-5.3-Flash-exl3 checkpoint + GLM-5.3 TP + vision tower support in engine)↗, incoai (GLM-5.3-Flash-DFlash2 BF16 drafter, CC BY-NC-ND 4.0)↗, 0xSero (k_hcfuse fused hyper-connection kernels, via Flun's repo)↗, Morrowmake (content-verified P2P check idea + benchmark prompt style)↗, bayley + arvkmr (fault probe idea + router-precision findings, vllm-170hx-glm5)↗, Z.ai (GLM-5.3-Flash base model)↗, msuiche (Weightless GLP-44 vector and specification)↗ · listed by alex.v.nesta

Four native active sequences on two 64 GiB CMP170HX cards; GLM-5.3-Flash EXL3 3.05bpw, TP2, with the Weightless GLP44 steering vector at alpha 2, FP16 recurrent state, Q8 GPU KV, D

GLM-5.3-Flash TP exllamav3 +2
GLM-5.3-Flash high effort on 2x CMP170HX EXL3 TP2 four slots

by alexvnesta (tensor-parallel fork: TP2, hybrid drafting, concurrent sessions, RAM tier, vision, NCCL backend)↗, Flun (original 2-card layer-split server + recipe this fork starts from)↗, turboderp (ExLlamaV3 engine + GLM-5.3-Flash-exl3 checkpoint + GLM-5.3 TP + vision tower support in engine)↗, incoai (GLM-5.3-Flash-DFlash2 BF16 drafter, CC BY-NC-ND 4.0)↗, 0xSero (k_hcfuse fused hyper-connection kernels, via Flun's repo)↗, Morrowmake (content-verified P2P check idea + benchmark prompt style)↗, bayley + arvkmr (fault probe idea + router-precision findings, vllm-170hx-glm5)↗, Z.ai (GLM-5.3-Flash base model)↗, msuiche (Weightless GLP-44 vector and specification)↗ · listed by alex.v.nesta

Four native active sequences on two 64 GiB CMP170HX cards; GLM-5.3-Flash EXL3 3.05bpw, TP2, with the Weightless GLP44 steering vector at alpha 2, FP16 recurrent state, Q8 GPU KV, D

GLM-5.3-Flash TP exllamav3 +2
GLM-5.3-Flash EXL3 3.05bpw on 2x CMP 170HX TP2 DFlash2 K7 hybrid drafting 393K (alexvnesta)

by alexvnesta (tensor-parallel fork: TP2, hybrid drafting, concurrent sessions, RAM tier, vision, NCCL backend)↗, Flun (original 2-card layer-split server + recipe this fork starts from)↗, turboderp (ExLlamaV3 engine + GLM-5.3-Flash-exl3 checkpoint + GLM-5.3 TP + vision tower support in engine)↗, incoai (GLM-5.3-Flash-DFlash2 BF16 drafter, CC BY-NC-ND 4.0)↗, 0xSero (k_hcfuse fused hyper-connection kernels, via Flun's repo)↗, Morrowmake (content-verified P2P check idea + benchmark prompt style)↗, bayley + arvkmr (fault probe idea + router-precision findings, vllm-170hx-glm5)↗, Z.ai (GLM-5.3-Flash base model)↗ · listed by localai-recipes

Tensor-parallel successor to Flun's 2x CMP 170HX layer-split recipe: ExLlamaV3 TP2 over both 64 GB cards with a 655,360-token Q8 KV pool (392,960-token request cap), DFlash2 K7 spe

GLM-5.3-Flash exllamav3 NVIDIA CMP 170HX 64GB ×2 (Ampere) 123.6 tok/s decode · 1316 tok/s prefill