GLM-5.3-Flash (321B MoE, ~18B active) turboderp EXL3 2.05bpw on two RTX 5090 + 64 GB DDR5: TabbyAPI on ExLlamaV3 with CPU-offloaded routed experts (96/layer GPU0 layers 3-22+MTP, 1
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.
6 recipes (2 beta hidden) · page 1 of 1
Community builds
Blackwell (4)
Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.
Community image TP2 DSpark K3 Vision serving recipe: B12X sparse MoE, FP8 KV, three draft layers, 1M context. Saved numbers from the KK comparison.
DeepSeek-V4-Flash-Vision-Exp vllm NVIDIA RTX PRO 6000 Blackwell 96GB ×2 169.2 tok/s decode · 8993 tok/s prefill
Community image TP2 DSpark K5 serving recipe: B12X sparse MoE, FP8 KV, InstantTensor loading, 1M context. Saved numbers from the KK comparison (Max-Q +6000).
DeepSeek-V4-Flash-0731 vllm NVIDIA RTX PRO 6000 Blackwell 96GB ×2 214.9 tok/s decode · 11167 tok/s prefill
Local Inference Lab production two-card serving config: TP2/DCP2, 8 concurrent seqs, MTP3 on B12X, lossless-CSF NVFP4 MoE (MXFP8-CSF-QAD weights, 188.87 GB), online MXFP8 attention
Ampere (2)
Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.
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,
Validated SGLang serving for the dense Qwen3.8-27B hybrid GDN vision-language model (48 Gated-DeltaNet + 16 gated-attention layers) on RTX 3090 24 GB: one digest-pinned container w