Drilldown: Recipe

DeepSeek V4.1 Flash on 4x 8 GB (alanoo fidelity build) (1) · DeepSeek V4.1 Flash on 4x 8 GB (GNmac) (1) · DeepSeek V4.1 Flash on 4x 8 GB (Morrowmake) (1) · DeepSeek V4.1 Flash on 4x 8 GB plus RTX PRO 6000 (ExLlamaV3 TP5) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Zanooda PP8) (1) · GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 TP2) (1) · GLM 5.3 Flash on 4x 8 GB (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 1x 8 GB (iIIusi0n SSD PLE) (1) · Qwen3.8 Flash Next on 2x 8 GB (DUFRelic PP2) (1) · Qwen3.8 Flash Next on 2x 8 GB (ElectroHobo W4A16 TP2) (1) · Qwen3.8 Flash Next on 2x 8 GB (mannydelrio PP2) (1)

DeepSeek-V4.1-Flash-1017 (5) · GLM-5.3-Flash (320B MoE, 18B active) (2) · 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) (2) · Qwen3.8-Flash-Next-Uncensored (refusal-removed, from orcarouter) (1)

AutoRound 3 bpw + MTP: klee100/Qwen3.8-Flash-Next-AutoRound-3bpw-MTP; 95.37 GiB BF16 PLE table on SSD (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 3.05 bpw: turboderp/GLM-5.3-Flash-exl3; DFlash2 drafter converted to EXL3 6 bpw (1) · EXL3 3.5 bpw (LibertAIDAI; routed experts 4 bpw on layers 0-9 and 30-39, 3 bpw on 10-29; attention and shared experts 6 bpw) plus the official Engram shards (1) · Hybrid: all 40 expert layers at 3 bits (LibertAI 2.9 bpw pack with layers 18-22 grafted from the 3.5 bpw pack), official FP8 dense tensors (1) · Hybrid: routed experts EXL3 (mostly 3 bpw, 2 bpw on layers 18-22) from LibertAI's 2.9 bpw pack; attention, shared experts, indexer and DSpark drafter official FP8; KV fp8_ds_mla (1) · Hybrid: routed experts EXL3 2.9 bpw (LibertAIDAI), everything else official FP8/BF16; KV BF16 (1) · NVFP4 (ModelOpt mixed precision): ProCreations/MiMo-V2.6-Flash-RL-NVFP4, run as 4-bit weights with BF16 activations through Marlin (1) · Official checkpoint as downloaded: MXFP4 routed experts as Marlin W4A16, MXFP8 dense as Marlin W8A16; KV fp8 (1) · W4A16 (INT4 weights, group size 128, FP16 activations): canada-quant/GLM-5.3-Flash-W4A16-MTP (1) · W4A16 INT4 g128 with the PLE table repacked INT4 g32: zankich/Qwen3.8-Flash-Next-W4A16-Merlin-INT4PLE-FP8KV; KV BF16 (1) · W4A16: halt95/Qwen3.8-Flash-Next-W4A16-Merlin (AutoRound INT4 g128 experts, INT8 GDN projections, FP8 n-gram table) (1)

ExLlamaV3 (patched, pinned) (1) · ExLlamaV3 fork (anoane/exllamav3-anemone) + TabbyAPI fork (anoane/tabbyAPI) (1) · GNmac-lab recipe image 1.2.0 (vLLM with sm_80 patches) plus three patches (1) · Morrowmake/vllm-cmp170hx (vLLM fork, container image) (2) · Morrowmake/vllm-cmp170hx image (Qwen EXL3 release) with patch files mounted read-only (1) · Morrowmake/vllm-cmp170hx image (tag qwen38-recipe-1.0.0) plus one mounted file (vLLM #58235 vision-sink fix) (1) · Morrowmake/vllm-cmp170hx image with patch files mounted read-only (1) · vLLM a5a30471 plus a 13-file downstream patch (native Linux AIO PLE reader) (1) · vLLM PR #56201 head (79a7108d) plus a 20-patch sm_80 series; image zanooda/vllm-sm80-ds41f:v41-sm80 (1) · vLLM v0.30.0 + zankich INT4-PLE plugin + six hash-guarded patch layers (1) · vLLM with a pinned sm_80 patch stack (built locally from source) (1) · wtdcode/vllm-backport 3142ded1 plus a two-file patch and two tinybeast PLE plugins (venv, no container) (1)

0.29.1rc1.dev402+ga5a30471f.ple1 (1) · GNmac-lab at 2ad5741ab1; image ds41-cmp170hx:1.2.0-fidelity (1) · recipe 0.2.1; engine 18305948ac (2) · recipe 0.3.1; engine 18305948ac (1) · recipe 1.0.0, engine a0c57b5237 (1) · recipe 1.2.0 (1) · recipe 1.8.0, engine 819146023f (1) · recipe 31318fd; patches 0001-0020 (1) · tag recipe-09 (309ef6d1); TabbyAPI deepseek-v41 (ce250ff) (1) · upstream dev 0f685aa9fd plus 9 patches; repo db01c256 (1) · vLLM v0.30.0 (ced6857a); plugin zankich/vllm v0.29.0z (6609bfef) (1) · vllm-backport 3142ded1 (1)

8 GB (13)

1 (2) · 2 (4) · 4 (6) · 8 (1)

PP2 (layer partition 25,23), no P2P (1) · PP2, MTP depth 3 (1) · PP8, partition 5,5,5,5,5,5,5,5 (1) · single card (2) · TP2 over NCCL (GPU P2P), DFlash2 K7 plus hybrid drafting (1) · TP2 with whole-expert expert parallel (1) · TP4 (default) or PP4 (1) · TP4 (default) or PP4 for x1/x4 links (1) · TP4 (P2P on); expert parallel off (1) · TP4 with expert parallel (96 whole experts per card) (1) · TP4, P2P on (1) · TP5 across four CMP 170HX and one RTX PRO 6000 Blackwell (native backend, reduces through host memory); MTP draft on the PRO (1)

1,048,576 (2) · 1,048,576 FP16 (1) · 262,144 (7) · 262,144 (up to 1,048,576) (1) · 262,144 advertised (tested through 32K) (1) · 392,960 per request; 655,360-token Q8 KV pool shared by two requests (1)

90 - 110 (3) · 110 - 300 (8) · 300 - 500 (2)

1,500 - 3,000 (6) · 3,000 - 3,800 (1) · 3,800 - 8,000 (6)

64 GB, --gpu-memory-utilization 0.94, TB_TORCH_MEM_CAP_GIB=61.5 (1) · 64 GB; weights 35.9 GB per rank (ranks 1-6), 37.6 GB rank 0, 46.3 GB rank 7 (1) · 64 GiB (64,911 MiB usable), GPU_MEMORY_UTILIZATION 0.98 (1) · 64 GiB exposed, --gpu-memory-utilization 0.95 (2) · 64 GiB, --gpu-memory-utilization 0.90 (1) · 64 GiB, --gpu-memory-utilization 0.95 (fixed) (1) · 64 GiB, --gpu-memory-utilization 0.96 (1) · 64 GiB, GPU_MEMORY_UTILIZATION 0.95 (1) · 64 GiB, GPU_UTIL 0.95 (fixed) (1) · 64 GiB; weights 45.5 GiB plus 10 GiB KV per card; GPU_UTIL 0.94 (fixed) (1) · about 62.9 / 62.3 GiB idle, peaks about 64.4 / 63.0 GiB with vision (1) · gpu_split 58 GB per CMP, 70 GB on the PRO (1)

140 W (200 W observed-draw abort guard) (1) · 150 W per CMP (PRO 400 W) (1) · 180 W (7) · 180 W (author's cards); about 170 W with a modest memory OC in his Discord numbers (1) · 180 W (nvidia-smi -pl 180) (1) · 180 W (one card unstable at 250 W) (1) · 200 W (1)

None (1) · 580 or newer (measured on 610.57.04) (2) · 580 or newer (measured on 610.57.04); open modules with HMM for the table-on-disk mode (1) · 610.43.03 (1) · 610.57.04 (1) · CUDA 13 capable; measured on 610.43.02 (1) · NVIDIA 580 or newer; P2P needs the Morrowmake/cmpunlocker build (2) · NVIDIA 610.43.02 (1) · NVIDIA open 610.43.02 from a cmpunlocker fork with a P2P patch (1) · NVIDIA open 610.57.04 patched with Morrowmake/cmpunlocker 1f2c498 (profile 8gb) (1) · nvidia-open 610.43.02 + cmpunlocker v0.5 or newer (1)

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 · 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 fork with P2P (without Morrowmake's TRAP31 patch) · cmpunlocker v0.5+ (sudo ./install.sh --profile=8gb --no-iommu) · cmpunlocker with the BAR1 P2P patches (64 GiB BAR1 per card) · Morrowmake/cmpunlocker 1f2c498; modprobe RmForceEnableGen2=1, RMPcieLinkSpeed=0x1, ForceP2P=0x11 · Other

Proven (4) · Reported (9)

alanoo (1) · anoane (1) · dufrelic (1) · greencandle9753 (1) · iIIusi0n (1) · mrmannyatx (1) · nathang6866 (3) · nestaa51 (1) · voidgiraffe (2) · Zanooda (1)

September 19, 2026 (1) · October 3, 2026 (1) · October 13, 2026 (1) · October 15, 2026 (1) · October 16, 2026 (1) · October 18, 2026 (1) · October 19, 2026 (1) · October 20, 2026 (1) · October 23, 2026 (2) · October 24, 2026 (1) · October 26, 2026 (1) · October 27, 2026 (1)

https://github.com/alanoo81/deepseek-v41-flash-4x-cmp170hx (1) · https://github.com/alexvnesta/glm53-flash-cmp170hx-tp (1) · https://github.com/anoane/09-deepseek-v41-flash-1017-exl3-tp5-1m (1) · https://github.com/DUFRelic/qwen38-flash-next-recipe (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/ElectroHobo/qwen38-flash-next-w4a16-2x-cmp170hx-recipe (1) · https://github.com/GNmac-lab/deepseek-v41-flash-1017-cmp170hx (1) · https://github.com/iIIusi0n/qwen3.8-flash-next-cmp170hx (1) · https://github.com/mannydelrio/qwen38-flash-next-2x-cmp170hx (1) · https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (1) · https://github.com/Morrowmake/glm53-flash-cmp170hx-recipe (1) · https://github.com/Zanooda/deepseek-v4.1-flash-cmp170hx (1)