{"slug":"ds4-1-flash-4x6000-jj-dspark-k7","title":"DeepSeek V4.1 Flash on 4x RTX PRO 6000 Blackwell \\x{2014} TP4 DSpark K7","summary":"Community image TP4 serving recipe: adaptive DSpark K7, RAM Engram ngram tables, 131K context cap. Saved numbers from the KK comparison.","license":"CC-BY-4.0","tier":"community","beta":false,"revision":{"no":2,"commit_sha":"218c00c639d52ad29638628a64740ea90069ffe1","content_hash":"77484355ac2ebdc80317b43b37868302df70cf22","created_at":"2026-10-20 21:54:52.540452-06","notes":"Compose: the ds41 r38 compose stack, GPUs 0-3, ENGRAM_TABLE_MEMORY=ram|disk. Adaptive depth mode; KK used adaptive DSpark K7."},"engine_source":{"type":"docker_image","git_url":"https://github.com/voipmonitor/vllm/tree/integration/jovian-reviewed-sources-20260911","base_engine":"vllm","pip_package":null,"base_version":"jovian-judgement r38 (community)","image_digest":"localinferencelab/vllm:jovian-judgement-community-20260914-r38","install_note":null,"pinned_commit":null},"credit":[{"name":"local-inference-lab","url":"https://github.com/local-inference-lab/rtx6kpro"}],"author":{"name":"localai-recipes","isSite":true},"uploaded_by":"localai-recipes","config":{"launch":["docker","compose","-f","the ds41 r38 compose stack","up","-d"]},"models":[{"slug":"deepseek-v4-1-flash","name":"DeepSeek-V4.1-Flash","hf_repo":"deepseek-ai/DeepSeek-V4.1-Flash","quant":"fp8"}],"hardware":[{"slug":"nvidia-rtx-pro-6000-blackwell-max-qx4","vendor":"nvidia","card":"RTX PRO 6000 Blackwell Max-Q","card_family":"rtx-pro-6000-blackwell","vram_gb":96,"device_count":4}],"generation":"blackwell","tags":["dspark","jovian-judgement"],"tasks":["chat","code"],"aa":{"aa_index":39,"aa_provenance":"measured","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash","aa_index_version":"Index v4.3.2","aa_methodology_version":"Index v4.3.2 (2026-10-18)","aa_published_fetched_at":"2026-10-20 21:49:11.309778-06","aa_family_slug":"deepseek-v4-1-flash","aa_resolved_slug":"deepseek-v4-1-flash"},"performance":[{"claimed_by":"submitter","metrics":"{\"points\": [{\"notes\": \"Saved JJ (KK comparison), 5-window median, ctx-0 decode\", \"concurrency\": 1, \"context_len\": 1, \"decode_tok_s\": 230.599999999999994315658113919198513031005859375}, {\"notes\": \"Saved JJ, aggregate C8\", \"concurrency\": 8, \"context_len\": 1, \"decode_tok_s\": 748.299999999999954525264911353588104248046875}, {\"notes\": \"Saved JJ, uncached nominal-32K prefill\", \"concurrency\": 1, \"context_len\": 32768, \"prefill_tok_s\": 17503}]}"}],"perf_points":[{"id":1732,"context_len":1,"prefill_tok_s":null,"decode_tok_s":230.599999999999994315658113919198513031005859375,"ttft_ms":null,"concurrency":1,"claimed_by":"submitter","notes":"Saved JJ (KK comparison), 5-window median, ctx-0 decode"},{"id":1733,"context_len":1,"prefill_tok_s":null,"decode_tok_s":748.299999999999954525264911353588104248046875,"ttft_ms":null,"concurrency":8,"claimed_by":"submitter","notes":"Saved JJ, aggregate C8"},{"id":1734,"context_len":32768,"prefill_tok_s":17503,"decode_tok_s":null,"ttft_ms":null,"concurrency":1,"claimed_by":"submitter","notes":"Saved JJ, uncached nominal-32K prefill"}],"agent":{"prompt":"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.","curl":"curl -fsSL https://localairecipes.com/api/v1/recipes/ds4-1-flash-4x6000-jj-dspark-k7.json"},"requirements":{"requires":["Docker (or a compatible OCI container runtime)","NVIDIA Container Toolkit (nvidia-container-toolkit) - exposes host GPUs to the container"],"driver_floor":{"cuda":null,"linux_min":null,"text":"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)"},"placeholders":["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."]},"artifacts":[],"links":{"self":"/api/v1/recipes/ds4-1-flash-4x6000-jj-dspark-k7.json","alternate":"/r/ds4-1-flash-4x6000-jj-dspark-k7","describedby":"/openapi.json"},"updated_at":"2026-10-20 21:54:52.540452-06","created_at":"2026-10-20 21:49:11.589137-06","speeds":{"decode_tok_s":230.599999999999994315658113919198513031005859375,"prefill_tok_s":17503,"leaderboard":"/api/v1/leaderboard.json"}}