320B MoE served on ONE 24 GB RTX 3090 with stock exllamav3 1.5.1 plus process-local monkeypatches: the 12,096 routed experts (42 MoE layers x 288, 8 picked per token per layer) tie
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.
7 recipes · page 1 of 1
Community builds
Ampere (6)
Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.
DeepSeek-V4.1-Flash-1017 (552B MoE + 196B Engram) quantized to 187.6 GB single GGUF (2.6127 bpw routed-expert average: 5717 PTQ1_0 / 2545 Q2_0 / 7098 Q3_K per-expert GPTQ with allo
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
GLM-5.3-Flash EXL3 3.05bpw on 2x RTX 3090 — vLLM + ExLlamaV3 CPU expert offload, 256K (DominikBucko)
GLM-5.3-Flash (turboderp EXL3 3.05bpw) tensor-parallel on 2x RTX 3090 24 GB + 128 GB system RAM: vendor vLLM image with the spele1100/vllm-glm53 GLM-5.3 overlay, ExLlamaV3 @ 499890
Single-card RTX 3090 recipe for Qwen3.8-Flash-Next (125B MoE) in the albucino W4A16-FP8PLE build (@ ef55414, same checkpoint as the 2x3090 runtime): the GPU holds attention + dense
Two-card RTX 3090 recipe for Qwen3.8-Flash-Next (125B MoE) in the albucino W4A16-FP8PLE build (Intel AutoRound INT4 backbone + FP8 PLE table + INT4 MTP draft, checkpoint @ ef55414)
AMD (1)
Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.
Qwen3.8-27B on a single AMD Radeon AI PRO R9700 (RDNA4 gfx1201, 32 GB) under Windows 11 + WSL2: vLLM radiance 0.9.3 fork pinned by image digest with AMD's official Quark AWQ-MXFP4