Drilldown: Recipe

DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE) (1) · DeepSeek V4.1 Flash on 6x 8 GB (TP6) (1) · Qwen3.8 Flash Next on 2x 8 GB (vektorprime PP2) (1) · Qwen3.8 Flash Next on 3x 8 GB (clee PP3) (1) · Qwen3.8 Flash Next on 4x 8 GB (1)

DeepSeek-V4.1-Flash-1017 (2) · Qwen3.8-Flash-Next (3)

AWQ INT4: cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4; 95 GiB BF16 PLE table in host RAM (FP8 table optional) (1) · AWQ W4A16: wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16 (1) · Hybrid: LibertAI EXL3 2.9 bpw routed experts (layers 0-39), official FP8/FP4 for attention, shared experts, head, draft and Engram; KV fp8_ds_mla (1) · Official checkpoint: dense MXFP8 through an SM80 Marlin W8A16 path, routed experts MXFP4 through W4A16; KV FP8 (1) · W4A16 AutoRound: Intel/Qwen3.8-Flash-Next-W4A16-AutoRound; 95.4 GiB BF16 PLE table streamed from NVMe; KV fp8 e4m3 (software-decoded on SM80) (1)

Custom SM80 vLLM (patched from public commit 79a7108d9) (1) · Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) · vLLM nightly + PR #53899 (a5530b9) + the repo's patch scripts (1) · vLLM nightly 7d0b4e57 plus the author's pure-Python fork clee/vllm-sm80 (branch q38fn/stack) (1) · wtdcode/vllm-backport (image lazymio/vllm-backport:latest-sm80) (1)

0.1.dev1+ga5530b90c.d20260829 (1) · latest-sm80 tag as of 2026-10-16 (1) · q38fn/stack on nightly-7d0b4e57 (1) · reports 0.0.0; patches/public-base-to-runtime.patch (109 files) (1) · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)

8 GB (5)

2 (1) · 3 (1) · 4 (2) · 6 (1)

PP2 with PLE CPU offload (1) · PP3, no P2P (works at PP2 on two cards) (1) · TP4 with expert parallel, MTP 3 (1) · TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1) · TP6 (virtual-head padding), PP1 (1)

1,000,000 (YaRN x4 from 262,144) (1) · 1,048,576 (1) · 1,048,576 (YaRN x4) (1) · 262,144 (1) · 262,144 (weights address 1,048,576) (1)

74.4 (1) · 75.4 (1) · 78.55 (1) · 116.49 (1) · 144.2 (1)

None (2) · 1,523 (1) · 2,101.4 (1) · 4,831 (1)

64 GB (1) · 64 GB, --gpu-memory-utilization 0.95 (1) · 64 GiB, gpu-memory-utilization 0.92 (1) · 64 GiB; weights PP0 39.48 GiB, PP1 45.53 GiB; --gpu-memory-utilization 0.9 (1) · about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (1)

None (4) · 140 W (1)

None (5)

None · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable build · cmpunlocker (64 GiB, 74 SMs); Morrowmake/cmpunlocker for P2P · amoghmunikote/cmpunlocker 6c442eeb (patch 0016 SM reconfig, 74 SMs) plus Bayley P2P patches 0011/0013/0015 · bayley/cmpunlocker 5a7bb4b, sudo ./install.sh --p2p --no-iommu · cmpunlocker (64 GB) · cmpunlocker (64 GiB) · cmpunlocker (64 GiB); P2P-capable driver for the NCCL backend · cmpunlocker (64 GiB, 74 SMs) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 · cmpunlocker 360acd7 (2026-08-06), 8 GB profile · cmpunlocker fork with P2P (without Morrowmake's TRAP31 patch) · cmpunlocker v0.5+ (sudo ./install.sh --profile=8gb --no-iommu) · cmpunlocker VRAM unlock (64 GB per card) · cmpunlocker VRAM unlock (64 GiB per card) · cmpunlocker VRAM unlock (65,536 MiB per card) · cmpunlocker with the BAR1 P2P patches (64 GiB BAR1 per card) · Morrowmake/cmpunlocker 1f2c498; modprobe RmForceEnableGen2=1, RMPcieLinkSpeed=0x1, ForceP2P=0x11 · Other

Proven (1) · Reported (4)

c133 (1) · CurtisAccelerate (1) · matstatman (1) · vektor_prime (1) · wgkbfcp (1)

August 2026 (1) · October 2026 (4)

https://discord.com/channels/1518634379604136178/1528826330454429706/1560602001908170753 (1) · https://github.com/clee/qwen3.8-flash-next-3x170hx (1) · https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-CMP170HX (1) · https://github.com/vektorprime/qwen38-flash-next-pp2 (1) · https://github.com/wgkbfcp/deepseek-v4.1-flash-1017-cmp170hx-recipe (1)