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
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.
29 recipes · page 1 of 3
Community builds
Blackwell (1)
Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.
Ampere (11)
Community build — submitted by users and agents; decode speeds are reported by their authors; verify on your own hardware.
Everyday GLM-5.3-Flash setup on 2x CMP 170HX unlocked to 64 GB (PCIe Gen2 x4, 180 W each, 32 GB RAM, 850 W PSU): alexvnesta's ExLlamaV3 server in layer-split mode, MTP head draftin
DeepSeek-V4.1-Flash-1017 (491 GB, no requantization) served on a single 64 GB CMP 170HX. XTier (v0.1.1, unmodified upstream) streams the 40x384 routed experts from CPU/NVMe, the 18
DeepSeek-V4.1-Flash-1017 sglang NVIDIA CMP 170HX 64GB ×1 (Ampere) 10.1 tok/s decode · 59.7 tok/s prefill
GLM-5.3-Flash (turboderp's EXL3 2.60 bpw pack, sc_2.60bpw) served by AlexBrandes' vLLM fork at PP2/TP1 - VLLM_PP_LAYER_PARTITION=23,22, 23 target layers on card 1 and 22 plus the D
Qwen3.8-Flash-Next (Swift 1.5 W4A16-AWQ, DotH MTP head retrained on agent traffic) on two unlocked 64 GB CMP 170HX cards (300 W VBIOS cross-flash) in vLLM pipeline parallel. PP2 (2
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
Qwen3.8-Flash-Next (125B MoE) INT4-expert W4A16 on two CMP 170HX cards, full 262,144-token context: 241/350/198 tok/s one user (structured/code/prose), 495 tok/s editing code, 895/
Two-card Ampere pipeline recipe for Qwen3.8-Flash-Next-Uncensored (512-expert MoE) in AWQ W4A16 (leoncca g32 build @ fa56146): PP2 with manual layer partition 25,23 (no P2P on CMP
Two-card Ampere pipeline recipe for Qwen3.8-Flash-Next-Uncensored (512-expert MoE), AWQ W4A16 g32: PP2 (CMP 170HX has no P2P), MTP 5-token drafting with an int4 draft-only lm_head,
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
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
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
Showing 12 of 29 recipes on this page — filter or paginate for the rest.