Drilldown: Recipe

DeepSeek V4.1 Flash on 4x 8 GB (GNmac) (1) · MiMo V2.6 Flash on 4x 8 GB (1) · Qwen3.8 Flash Next on 1x 8 GB (ElectroHobo 3 bpw) (1)

DeepSeek-V4.1-Flash-1017 (1) · MiMo-V2.6-Flash-RL (309B MoE, 15B active; text, image, video and audio input) (1) · Qwen3.8-Flash-Next (125B MoE per the recipe) (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) · 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) · NVFP4 (ModelOpt mixed precision): ProCreations/MiMo-V2.6-Flash-RL-NVFP4, run as 4-bit weights with BF16 activations through Marlin (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 with a pinned sm_80 patch stack (built locally from source) (1)

recipe 0.2.1; engine 18305948ac (2) · recipe 1.2.0 (1)

8 GB · Other · None

1 (1) · 4 (2)

single card (1) · TP4 (default) or PP4 for x1/x4 links (1) · TP4 (P2P on); expert parallel off (1)

1,048,576 (1) · 262,144 (1) · 262,144 (up to 1,048,576) (1)

258 (1) · 274.9 (1) · 296.4 (1)

2,416 (1) · 2,722 (1) · 4,243 (1)

64 GiB, --gpu-memory-utilization 0.95 (fixed) (1) · 64 GiB, GPU_MEMORY_UTILIZATION 0.95 (1) · 64 GiB; weights 45.5 GiB plus 10 GiB KV per card; GPU_UTIL 0.94 (fixed) (1)

180 W (2) · 180 W (nvidia-smi -pl 180) (1)

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

cmpunlocker (64 GiB, 74 SMs) (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable build (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 (1)

Proven (1) · Reported (2)

greencandle9753 (1) · nathang6866 (2)

October 18, 2026 (1) · October 23, 2026 (1) · October 26, 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/GNmac-lab/deepseek-v41-flash-1017-cmp170hx (1)