Drilldown: Recipe

DeepSeek V4.1 Flash heretic on 4x 8 GB (1) · DeepSeek V4.1 Flash on 2x 8 GB (Project Maya) (1) · DeepSeek V4.1 Flash on 4x 8 GB (alanoo fidelity build) (1) · DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE) (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) · GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 layer split) (1) · GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 TP2) (1) · GLM 5.3 Flash on 2x 8 GB (Project Maya) (1) · GLM 5.3 Flash on 3x 8 GB (1) · GLM 5.3 Flash on 4x 8 GB (1) · MiMo V2.6 Flash on 4x 8 GB (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) · 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 (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 (5) · DeepSeek-V4.1-Flash-1017 (748B in the Maya README) (1) · DeepSeek-V4.1-Flash-1017 heretic (pqhaz abliteration) (1) · GLM-5.3-Flash (320B MoE, 18B active) (4) · GLM-5.3-Flash (321B in the Maya README) (1) · MiMo-V2.6-Flash-RL (309B MoE, 15B active; text, image, video and audio input) (1) · Qwen3.8-Flash-Next (6) · Qwen3.8-Flash-Next (125B MoE per the recipe) (1) · Qwen3.8-Flash-Next-Uncensored (refusal-removed, from orcarouter) (1)

AWQ INT4: cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4; 95 GiB BF16 PLE table in host RAM (FP8 table optional) (1) · AWQ W4A16 g32 (leoncca/Qwen3.8-Flash-Next-Uncensored-AWQ-g32); PLE table converted to INT4 and served from SSD (1) · AWQ W4A16: wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16 (1) · EXL3 3.05 bpw: turboderp/GLM-5.3-Flash-exl3 (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) · EXL3 5.05 bpw; PLE (n-gram) table read from SSD (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: 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) · 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 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) · Maya GGUF (Maya-S 340 GB or Maya-XS 277 GB; Engram tables stay on SSD) (1) · Maya-M GGUF (116 GB), every expert in VRAM; Maya-S (96.5 GB) and Maya-S24 (94.7 GB) also reported (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) · W4A16 (INT4 weights, group size 128, FP16 activations): canada-quant/GLM-5.3-Flash-W4A16-MTP (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) · W4A16 INT4 g128 with the PLE table repacked INT4 g32: zankich/Qwen3.8-Flash-Next-W4A16-Merlin-INT4PLE-FP8KV; KV BF16 (1) · W4A16, about 4.3 bpw, 163 GiB on disk (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 1.5.4 (built for SM80) with a small OpenAI-compatible server (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 (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) · Morrowmake/vllm-cmp170hx (EXL3 path) (1) · Morrowmake/vllm-cmp170hx (via the glm53-flash-cmp170hx-recipe) (1) · Morrowmake/vllm-cmp170hx (vLLM fork, container image) (3) · 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) · Project Maya (Strata and llama.cpp lineage) (1) · Project Maya (Strata and llama.cpp lineage, EXL3 loading, DFlash2 drafter) (1) · vLLM 0.29.1rc1 nightly plus the checkpoint author's patches (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) · 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 (image lazymio/vllm-backport:latest-sm80) (1) · wtdcode/vllm-backport 3142ded1 plus a two-file patch and two tinybeast PLE plugins (venv, no container) (1)

None (2) · 0.1.dev1+ga5530b90c.d20260829 (1) · Flun/glm53-flash-cmp170hx-exl3 at 5933112 (1) · GNmac-lab at 2ad5741ab1; image ds41-cmp170hx:1.2.0-fidelity (1) · latest-sm80 tag as of 2026-10-16 (1) · not stated (1) · q38fn/stack on nightly-7d0b4e57 (1) · recipe 0.2.1; engine 18305948ac (1) · recipe 0.3.1; engine 18305948ac (1) · recipe 1.0.0 (commit d4d1f525), engine a0c57b52 (1) · recipe 1.0.0, engine a0c57b5237 (1) · recipe 1.2.0 (1) · recipe 1.8.0, engine 819146023f (1) · tag qwen38-recipe-1.0.0, engine 18305948ac (1) · tag recipe-09 (309ef6d1); TabbyAPI deepseek-v41 (ce250ff) (1) · upstream dev 0f685aa9fd plus 9 patches; repo db01c256 (1) · v1.0.6 (this row) (1) · vLLM v0.30.0 (ced6857a); plugin zankich/vllm v0.29.0z (6609bfef) (1) · vllm-backport 3142ded1 (1) · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)

8 GB · Other · None

2 (10) · 3 (2) · 4 (9)

engine-managed expert tiering across VRAM, host RAM and NVMe (1) · engine-managed split with expert tiering across VRAM, RAM and NVMe (1) · layer split (no tensor parallel), no P2P (1) · PP2 (layer partition 25,23), no P2P (1) · PP2 with PLE CPU offload (1) · PP2, MTP 3, no P2P (1) · PP2, MTP depth 3 (1) · PP3 (1) · PP3, no P2P (works at PP2 on two cards) (1) · TP2 over NCCL (GPU P2P), DFlash2 K7 plus hybrid drafting (1) · TP2 with expert parallel (1) · TP2 with whole-expert expert parallel (1) · TP4 (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 with expert parallel, MTP 3 (1) · TP4, P2P on (1) · TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1) · TP5 across four CMP 170HX and one RTX PRO 6000 Blackwell (native backend, reduces through host memory); MTP draft on the PRO (1)

None (2) · 1,000,000 (YaRN x4 from 262,144) (1) · 1,048,576 (1) · 1,048,576 (YaRN x4) (1) · 1,048,576 FP16 (1) · 262,144 (9) · 262,144 (256K in the post) (1) · 262,144 (up to 1,048,576) (1) · 262,144 (weights address 1,048,576) (1) · 392,960 (profile q8_384k) (1) · 392,960 per request; 655,360-token Q8 KV pool shared by two requests (1) · about 1,000,000 (8-bit KV cache) (1)

None (1) · 60 - 80 (5) · 80 - 130 (4) · 130 - 200 (6) · 200 - 500 (5)

None (4) · 0 - 2,100 (3) · 2,100 - 2,500 (4) · 2,500 - 4,000 (5) · 4,000 - 8,000 (5)

64 GB (4) · 64 GB, --gpu-memory-utilization 0.94, TB_TORCH_MEM_CAP_GIB=61.5 (1) · 64 GiB (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 0.92 (miner co-resident) (1) · 64 GiB, --gpu-memory-utilization 0.95 (1) · 64 GiB, gpu-memory-utilization 0.92 (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) · 64 GiB; weights PP0 39.48 GiB, PP1 45.53 GiB; --gpu-memory-utilization 0.9 (1) · about 58 GiB of 64 GiB (116.6 GiB resident across both) (1) · about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (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)

None (10) · 140 W (1) · 140 W (200 W observed-draw abort guard) (1) · 150 W per CMP (PRO 400 W) (1) · 180 W (5) · 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) · 200 W (1)

None (11) · 580 or newer (measured on 610.57.04) (1) · 580 or newer (measured on 610.57.04); open modules with HMM for the table-on-disk mode (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 (11) · amoghmunikote/cmpunlocker 6c442eeb (patch 0016 SM reconfig, 74 SMs) plus Bayley P2P patches 0011/0013/0015 (1) · cmpunlocker (64 GiB); P2P-capable driver for the NCCL backend (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable build (2) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 (1) · cmpunlocker (64 GiB, 74 SMs); Morrowmake/cmpunlocker for P2P (2) · cmpunlocker fork with P2P (without Morrowmake's TRAP31 patch) (1) · cmpunlocker v0.5+ (sudo ./install.sh --profile=8gb --no-iommu) (1) · Morrowmake/cmpunlocker 1f2c498; modprobe RmForceEnableGen2=1, RMPcieLinkSpeed=0x1, ForceP2P=0x11 (1)

Proven (5) · Reported (16)

68x0 (1) · alanoo (1) · anoane (1) · c133 (1) · CurtisAccelerate (1) · darkmaniac7 (1) · dufrelic (1) · greencandle9753 (1) · matstatman (1) · mrmannyatx (1) · nathang6866 (2) · nestaa51 (1) · pcsv. (1) · plean. (1) · shirogeek (1) · vektor_prime (1) · voidgiraffe (3) · ZackO2o (1)

August 2026 (1) · October 2026 (19)

https://discord.com/channels/1518634379604136178/1518695289278566450/1561743826945843304 (1) · https://discord.com/channels/1518634379604136178/1528826330454429706/1560602001908170753 (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/clee/qwen3.8-flash-next-3x170hx (1) · https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-CMP170HX (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-w4a16-2x-cmp170hx-recipe (1) · https://github.com/Flun/glm53-flash-cmp170hx-exl3 (1) · https://github.com/GNmac-lab/deepseek-v41-flash-1017-cmp170hx (1) · https://github.com/mannydelrio/qwen38-flash-next-2x-cmp170hx (1) · https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (2) · https://github.com/Morrowmake/glm53-flash-cmp170hx-recipe (1) · https://github.com/Morrowmake/qwen38-flash-next-cmp170hx-recipe (1) · https://github.com/mw00/project-maya#how-fast-is-it (2) · https://github.com/vektorprime/qwen38-flash-next-pp2 (1) · https://www.bozocentral.com/2x-cmp170hx-qwen3-flash-next (1)