Drilldown: Recipe

GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 layer split) (1) · GLM 5.3 on 8x 8 GB (vllm-170hx-glm5) (1) · Qwen3.8 Flash Next on 1x 8 GB (iIIusi0n SSD PLE) (1)

GLM-5.3 (full 78-layer DSA MoE, not Flash) (1) · GLM-5.3-Flash (320B MoE, 18B active) (1) · Qwen3.8-Flash-Next (1)

AutoRound 3 bpw + MTP: klee100/Qwen3.8-Flash-Next-AutoRound-3bpw-MTP; 95.37 GiB BF16 PLE table on SSD (1) · EXL3 3.05 bpw: turboderp/GLM-5.3-Flash-exl3 (1) · GLM-5.3-Int4-Int8Mix-AWQ-g64; drafter incoai/GLM-5.3-DFlash2 (1)

ExLlamaV3 1.5.4 (built for SM80) with a small OpenAI-compatible server (1) · Morrowmake/vllm-cmp170hx branch ampere-glm53 plus fail-closed source patches (1) · vLLM a5a30471 plus a 13-file downstream patch (native Linux AIO PLE reader) (1)

None · recipe 0.2.1; engine 18305948ac · 0.1.dev1+ga5530b90c.d20260829 · 0.29.1rc1.dev402+ga5a30471f.ple1 · Deepinfer-SM80 2a828fc lineage; vLLM v0.28.1rc0 base · Deepinfer-SM80, vLLM v0.28.1rc0 base · Flun/glm53-flash-cmp170hx-exl3 at 5933112 · GNmac-lab at 2ad5741ab1; image ds41-cmp170hx:1.2.0-fidelity · latest-sm80 tag as of 2026-10-16 · not stated · q38fn/stack on nightly-7d0b4e57 · recipe 0.3.1; engine 18305948ac · recipe 1.0.0 (commit d4d1f525), engine a0c57b52 · recipe 1.0.0, engine a0c57b5237 · recipe 1.2.0 · recipe 1.8.0, engine 819146023f · recipe 31318fd; patches 0001-0020 · reports 0.0.0; patches/public-base-to-runtime.patch (109 files) · tag qwen38-recipe-1.0.0, engine 18305948ac · tag recipe-09 (309ef6d1); TabbyAPI deepseek-v41 (ce250ff) · upstream dev 0f685aa9fd plus 9 patches; repo db01c256 · v1.0.6 (this row) · vLLM 0.30.1rc1, fork commit 378c37b0 · vLLM v0.30.0 (ced6857a); plugin zankich/vllm v0.29.0z (6609bfef) · vllm-backport 3142ded1 · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec · Other

8 GB (3)

1 (1) · 2 (1) · 8 (1)

layer split (no tensor parallel), no P2P (1) · PP8 (also PP9 and PP10), TP1 (1) · single card (1)

1,048,576 per request (1) · 262,144 advertised (tested through 32K) (1) · 392,960 (profile q8_384k) (1)

48.7 (1) · 60 (1) · 110.99 (1)

None (1) · 1,833 (1) · 2,636 (1)

64 GiB, --gpu-memory-utilization 0.96 (1) · 64 GiB, GPU_UTIL 0.96 at PP8 (1) · about 58 GiB of 64 GiB (116.6 GiB resident across both) (1)

None (1) · 170 W (author's 10-card run) (1) · 180 W (1)

None (2) · 610.43.03 (1)

None (2) · cmpunlocker (64 GiB) (1)

Proven (3)

68x0 (1) · iIIusi0n (1) · reala7096 (1)

September 19, 2026 (1) · September 29, 2026 (1) · October 20, 2026 (1)

https://github.com/arvkmr/vllm-170hx-glm5 (1) · https://github.com/Flun/glm53-flash-cmp170hx-exl3 (1) · https://github.com/iIIusi0n/qwen3.8-flash-next-cmp170hx (1)