The proven 3-card pipeline-parallel recipe on CMP 170HX (sm_80, 64GB unlocked): PP=3 with manual layer partition 15,16,12 at util 0.98, FP8 KV, block-size 256, DSpark block draftin
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.
12 recipes (2 beta hidden) · page 1 of 1
Ampere (1)
Community builds
Blackwell (6)
Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.
GLM-5.3-Flash NVFP4 (nvidia checkpoint) served by Enntity's Atlas engine with tensor+expert parallelism across two DGX Sparks over one ConnectX-7 cable, DFlash2 speculative decodin
GLM-5.3-Flash exlr8: MoE layers are EXL3-trellis units decoded by the custom exlr8 MoE kernel; dense linears stay FP8/NVFP4. One release carries three expert widths (k2/k3/k4 = 2/3
Recipe by ttlogan. Production 2-node GB10 (ASUS GX10 / DGX Spark) cluster serve of jpezzulli/OrcaRouter-Qwen3.8-Flash-Next-Uncensored-ModelOpt-NVFP4 (OrcaRouter uncensored weights
Qwen3.8-Flash-Next sglang NVIDIA DGX Spark 128GB ×2 (Blackwell) 40.3 tok/s decode · 2936.7 tok/s prefill
Community image TP4 serving recipe: MTP3 draft, B12X MoE, FP8 KV, 1M context. Saved five-window medians (Max-Q +6000), the reference the Karmic Kraken report compares against.
Community image TP4 serving recipe: DFlash2 K7 offline-MXFP8 draft, B12X MoE, FP8 KV, 1M context. Saved five-window medians (Max-Q +6000).
Community image TP4 serving recipe: adaptive DSpark K7, RAM Engram ngram tables, 131K context cap. Saved numbers from the KK comparison.
DeepSeek-V4.1-Flash vllm NVIDIA RTX PRO 6000 Blackwell 96GB ×4 230.6 tok/s decode · 17503 tok/s prefill
Ampere (5)
Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.
MTP-4 production recipe for Qwen3.8-Flash-Next-Uncensored (leoncca AWQ-g32) on 3x CMP 170HX (SM80 cards unlocked to 64 GiB): PP3 partition 17,17,14 (no GPU P2P on this pairing; the
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
Working PP3 recipe for Qwen3.8-Flash-Next (Qwen4Exp 180B-A6B MoE, Intel INT4 W4A16 AutoRound) on 3x CMP 170HX (SM80, unlocked 64 GiB each): the 95.4 GiB BF16 PLE n-gram table strea
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
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