DeepSeek V4.1 Flash on 4x RTX PRO 6000 Blackwell \x{2014} TP4 DSpark K7

community Community submission — verify on your own hardware.

recipe by local-inference-lab↗ · listed by localai-recipes

revision r2 · commit 218c00c639 · updated 10 d ago · license CC-BY-4.0

Community image TP4 serving recipe: adaptive DSpark K7, RAM Engram ngram tables, 131K context cap. Saved numbers from the KK comparison.

Launch command

docker compose -f 'the ds41 r38 compose stack' up -d

Use this recipe with your agent

Paste this into any agent chat — it fetches and applies the recipe:

Fetch https://localairecipes.com/api/v1/recipes/ds4-1-flash-4x6000-jj-dspark-k7.json and apply the inference recipe it describes (engine flags, model, quant, context) to my setup. Ask before overwriting any existing config.

Or fetch it directly:

curl -fsSL https://localairecipes.com/api/v1/recipes/ds4-1-flash-4x6000-jj-dspark-k7.json

Engine

vllm · source↗ · localinferencelab/vllm:jovian-judgement-community-20260914-r38↗

Model

DeepSeek-V4.1-Flash (fp8) · deepseek-ai/DeepSeek-V4.1-Flash↗
AA intelligence 39 (Artificial Analysis · measured)

Hardware

NVIDIA RTX PRO 6000 Blackwell 96GB ×4

Performance

Speed by context

Context	Conc.	Prefill	Decode	TTFT
1	1	—	230.6 tok/s	—	reported
1	8	—	748.3 tok/s	—	reported
32,768	1	17503 tok/s	—	—	reported

prefill = prompt processing · decode = generation. All decode/prefill figures are shown as reported.

Install requirements

Docker (or a compatible OCI container runtime)
NVIDIA Container Toolkit (nvidia-container-toolkit) - exposes host GPUs to the container

NVIDIA driver floor: unknown - check the image tag

Source: NVIDIA CUDA Toolkit Release Notes - driver compatibility tables (https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/, fetched 2026-10-03).

Map the placeholders to your rig

Hardware-bound values in this recipe (device counts, bind-mount paths, utilization, ports) describe the author's machine, not yours - map them to your own rig before launching. Keep the engine flags, model, quant, and parallelism strategy; adjust paths and ports to the hardware you actually have.
GPU identity: list your GPUs with `nvidia-smi -L` and substitute your own GPU UUIDs/indices wherever the recipe pins the author's.
Model directory: bind-mount paths are author-side - point them at your own mount where the model files live.
Host port: pick a free port on your machine and publish the container there; keep the in-container port unchanged.

Revision notes

Compose: the ds41 r38 compose stack, GPUs 0-3, ENGRAM_TABLE_MEMORY=ram|disk. Adaptive depth mode; KK used adaptive DSpark K7.

Revision history

bfdf9daa3e history: re-squash corpus to a single root commit after the slug reconciliation (prior tip kept at refs/lar-archive/pre-single-slug-resquash) 25 d ago

Fork

Export

recipe.yaml (raw)