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,
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.
8 recipes · page 1 of 1
Community builds
Ampere (7)
Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.
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
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
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
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
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
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
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