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)
Refine

Source:

Engine
Model
Quant
Storage requirement
Feature tags

Reset

Filters: glm-5-3-flash dgx-spark 170hx-x2 dgx-spark-x2 clear all

8 recipes · 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.

Ampere (6)

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

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
GLM-5.3-Flash EXL3 3.05bpw on 2x CMP 170HX — DFlash2 K7 Q8 KV 384K (Flun)

by Flun (recipe, stack, profiles, drafter conversion)↗, turboderp (ExLlamaV3 engine + GLM-5.3-Flash-exl3 checkpoint)↗, incoai (GLM-5.3-Flash-DFlash2 BF16 drafter, CC BY-NC-ND 4.0)↗, 0xSero (k_hcfuse fused decode kernels)↗, MiaAI-Lab (GLM-5.3-Flash-EXL3-2x-DGX-Sparks — conversion reference)↗, Z.ai (GLM-5.3-Flash base model)↗ · listed by localai-recipes

First ExLlamaV3 serving recipe on 2x CMP 170HX: full-VRAM HBM-resident GLM-5.3-Flash EXL3 3.05bpw (~116.6 GiB across 2x64GB, no CPU/SSD tier) with DFlash2 K7 speculative decoding —

GLM-5.3-Flash exllamav3 NVIDIA CMP 170HX 64GB ×2 (Ampere) 90 tok/s decode