Drilldown: Recipe

DeepSeek V4.1 Flash heretic on 4x 8 GB (1) · DeepSeek V4.1 Flash on 4x 8 GB (Morrowmake) (1) · DeepSeek V4.1 Flash on 6x 8 GB (Deepinfer-SM80 TP2 x PP3) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Deepinfer-SM80 TP4 x PP2) (1) · MiMo V2.6 Flash on 4x 8 GB (1) · Qwen3.8 Flash Next on 1x 8 GB (ElectroHobo 3 bpw) (1) · Qwen3.8 Flash Next on 2x 8 GB (mannydelrio PP2) (1) · Qwen3.8 Flash Next on 2x 8 GB (Morrowmake EXL3) (1) · Qwen3.8 Flash Next on 2x 8 GB (Plean PP2) (1) · Qwen3.8 Flash Next on 2x 8 GB (Qwen-Flash-SM80, GDS TEP2) (1)

DeepSeek-V4.1-Flash-1017 (3) · DeepSeek-V4.1-Flash-1017 heretic (pqhaz abliteration) (1) · MiMo-V2.6-Flash-RL (309B MoE, 15B active; text, image, video and audio input) (1) · Qwen3.8-Flash-Next (2) · Qwen3.8-Flash-Next (125B MoE per the recipe) (1) · Qwen3.8-Flash-Next (nvidia/Qwen3.8-Flash-Next-NVFP4, revision fc694b54, 11 shards, 132.68 GB) (1) · Qwen3.8-Flash-Next-Uncensored (refusal-removed, from orcarouter) (1)

AutoRound mixed 2/3-bit (klee100, 2.998 effective bpw, 47 GiB on card) plus halt95's FP8 n-gram table in host RAM (1) · AWQ W4A16 g32 (leoncca/Qwen3.8-Flash-Next-Uncensored-AWQ-g32); PLE table converted to INT4 and served from SSD (1) · EXL3 5.05 bpw; PLE (n-gram) table read from SSD (1) · Hybrid: routed experts EXL3 2.9 bpw (LibertAIDAI), everything else official FP8/BF16 with the 38 heretic attn.wo_b tensors (1) · Hybrid: routed experts EXL3 2.9 bpw (LibertAIDAI), everything else official FP8/BF16; KV BF16 (1) · Mixed INT4 AutoRound (Minachist/Qwen3.8-Flash-Next-INT4-Mixed-AutoRound, about 65 GB) with the full BF16 PLE table on NVMe (1) · NVFP4 (ModelOpt mixed precision): ProCreations/MiMo-V2.6-Flash-RL-NVFP4, run as 4-bit weights with BF16 activations through Marlin (1) · NVFP4 main weights through Marlin (no native FP4 on sm_80), mixed FP8 and BF16 MTP weights, FP8 PLE table (about 51.2 GB) kept on NVMe (1) · Official checkpoint (FP8 dense, FP4 experts); software FP8 on sm_80 (2)

Morrowmake/vllm-cmp170hx (vLLM fork, container image) · vLLM PR #56201 head (79a7108d) plus the two Deepinfer-SM80 patches and 30 drop-in modules · Custom SM80 vLLM (patched from public commit 79a7108d9) · ExLlamaV3 (patched, pinned) · ExLlamaV3 1.5.4 (built for SM80) with a small OpenAI-compatible server · ExLlamaV3 fork (anoane/exllamav3-anemone) + TabbyAPI fork (anoane/tabbyAPI) · GNmac-lab recipe image 1.2.0 (vLLM with sm_80 patches) plus three patches · Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels · Morrowmake/vllm-cmp170hx (EXL3 path) · Morrowmake/vllm-cmp170hx (via the glm53-flash-cmp170hx-recipe) · Morrowmake/vllm-cmp170hx branch ampere-glm53 plus fail-closed source patches · Morrowmake/vllm-cmp170hx image (Qwen EXL3 release) with patch files mounted read-only · Morrowmake/vllm-cmp170hx image (tag qwen38-recipe-1.0.0) plus one mounted file (vLLM #58235 vision-sink fix) · Morrowmake/vllm-cmp170hx image with patch files mounted read-only · Project Maya (Strata and llama.cpp lineage) · Project Maya (Strata and llama.cpp lineage, EXL3 loading, DFlash2 drafter) · Qwen-Flash-SM80 overlay on vllm/vllm-openai:qwen38-flash-next (digest-pinned), FlashInfer PCIe IPC AllReduce, GDS/cuFile over NVMe P2PDMA · vLLM · vLLM (build not stated) · vLLM 0.29.1rc1 nightly plus the checkpoint author's patches · vLLM a5a30471 plus a 13-file downstream patch (native Linux AIO PLE reader) · vLLM nightly + PR #53899 (a5530b9) + the repo's patch scripts · vLLM nightly 7d0b4e57 plus the author's pure-Python fork clee/vllm-sm80 (branch q38fn/stack) · vLLM PR #56201 head (79a7108d) plus a 20-patch sm_80 series; image zanooda/vllm-sm80-ds41f:v41-sm80 · vLLM v0.30.0 + zankich INT4-PLE plugin + six hash-guarded patch layers · vLLM with a pinned sm_80 patch stack (built locally from source) · vLLM: 344303947's fork of wtdcode/vllm-backport (shadow source layer, staged Marlin repack, exact-size Engram pinning) · vLLM: haosdent/vllm branch dsv4-flash-a100 plus allover326's 7 patches (DSpark under PP, sm_80 prefill top-k fallback, logits row chunking) · vLLM: haosdent/vllm branch dsv4-flash-a100 with a vendored copy of allover326's 7 patches (image dsv4-a100:devel) · vLLM: hyd998877/vllm_170hx_glm53-flash-exl3-optimized with kaka86mm's overlay patches; exllamav3 1.4.8 · vLLM: official vllm/vllm-openai:glm53-flash image plus promisezackr's 24 patches (SM8x base from 344303947/vllm170hx, pipeline parallel for GLM-5.3-Flash, DFlash2 under PP8) · vLLM: the vllm/vllm-openai:qwen38-flash-next image with zebgop-ops patches 0001 to 0016 (never 0008-WITHDRAWN) and three ported files · wtdcode/vllm-backport (image lazymio/vllm-backport:latest-sm80) · wtdcode/vllm-backport 3142ded1 plus a two-file patch and two tinybeast PLE plugins (venv, no container) · Other · None

None (1) · Deepinfer-SM80 2a828fc lineage; vLLM v0.28.1rc0 base (1) · Deepinfer-SM80, vLLM v0.28.1rc0 base (1) · recipe 0.2.1; engine 18305948ac (2) · recipe 1.0.0 (commit d4d1f525), engine a0c57b52 (1) · recipe 1.0.0, engine a0c57b5237 (1) · tag qwen38-recipe-1.0.0, engine 18305948ac (1) · v0.3.0 (commit 4d229f1, 2026-10-14); base vLLM 0.1.dev20073+g8e685d198 (1) · vllm-backport 3142ded1 (1)

8 GB (10)

1 (1) · 2 (4) · 4 (3) · 6 (1) · 8 (1)

PP2 (layer partition 25,23), no P2P (1) · PP2, MTP 3, no P2P (1) · single card (1) · TEP2 (TP2 plus expert parallel), MTP 6; one card at PCIe Gen2 x16 (x16 mod), one at Gen2 x4; GPU P2P required (1) · TP2 with expert parallel (1) · TP2 x PP3, partition 14,14,12 (1) · TP4 (1) · TP4 (P2P on); expert parallel off (1) · TP4 with expert parallel (96 whole experts per card) (1) · TP4 x PP2, partition 20,20 (1)

1,048,576 (3) · 262,144 (6) · 262,144 (256K in the post) (1)

150 - 170 (5) · 170 - 300 (5)

1,000 - 3,000 (4) · 3,000 - 8,000 (6)

64 GB (1) · 64 GB, --gpu-memory-utilization 0.93 (v0.3.0) (1) · 64 GB, --gpu-memory-utilization 0.94, TB_TORCH_MEM_CAP_GIB=61.5 (1) · 64 GiB (1) · 64 GiB exposed, --gpu-memory-utilization 0.95 (1) · 64 GiB, --gpu-memory-utilization 0.92 (miner co-resident) (1) · 64 GiB, --gpu-memory-utilization 0.95 (2) · 64 GiB, --gpu-memory-utilization 0.95 (fixed) (1) · 64 GiB; weights 45.5 GiB plus 10 GiB KV per card; GPU_UTIL 0.94 (fixed) (1)

None (6) · 180 W (4)

None (5) · 580 or newer (measured on 610.57.04) (2) · NVIDIA 580 or newer; P2P needs the Morrowmake/cmpunlocker build (1) · NVIDIA open 610.43.03, CUDA 13.0 (1) · nvidia-open 610.43.02 + cmpunlocker v0.5 or newer (1)

None (5) · bayley/cmpunlocker 5a7bb4b, sudo ./install.sh --p2p --no-iommu (1) · cmpunlocker (64 GiB, 74 SMs) (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable build (1) · cmpunlocker (64 GiB, 74 SMs); Morrowmake/cmpunlocker for P2P (1) · cmpunlocker v0.5+ (sudo ./install.sh --profile=8gb --no-iommu) (1)

Reported · Proven · Other · None

darkmaniac7 (1) · HalfVulpes (2) · mrmannyatx (1) · nathang6866 (2) · nguyenthimy2022kg-alt (1) · plean. (1) · voidgiraffe (2)

September 8, 2026 (1) · October 7, 2026 (1) · October 15, 2026 (1) · October 16, 2026 (1) · October 18, 2026 (1) · October 23, 2026 (1) · October 24, 2026 (1) · October 28, 2026 (2) · October 29, 2026 (1)

https://github.com/ElectroHobo/mimo-v26-flash-cmp170hx-recipe (1) · https://github.com/ElectroHobo/qwen38-flash-next-3bpw-1x-cmp170hx-recipe (1) · https://github.com/HalfVulpes/Deepinfer-SM80 (2) · https://github.com/mannydelrio/qwen38-flash-next-2x-cmp170hx (1) · https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (2) · https://github.com/Morrowmake/qwen38-flash-next-cmp170hx-recipe (1) · https://github.com/nguyenthimy2022kg-alt/Qwen-Flash-SM80-170HX (1) · https://www.bozocentral.com/2x-cmp170hx-qwen3-flash-next (1)