{"slug":"qwen3-8-flash-next-1x6000-kk-mtp3","title":"Qwen3.8-Flash-Next on RTX PRO 6000 Blackwell \u2014 Karmic Kraken TP1 MTP3","summary":"Karmic Kraken TP1 serving recipe: MTP3, CPU PLE, fixed 8-GiB KV budget, FP8 KV, 262K context. Qualified with a cached-restart series kept in the evidence.","license":"CC-BY-4.0","tier":"community","beta":true,"revision":{"no":3,"commit_sha":"d603558ebe41d9df3c8584017c7ba5d3bea1e044","content_hash":"176a6a704adb8b4d72798b8b58ef0e7a9a5294c6","created_at":"2026-10-20 15:34:04.148288-06","notes":"Benchmark-qualified configuration from local-inference-lab/rtx6kpro (Karmic Kraken serving report). Five warmed 30-second windows per cell on RTX PRO 6000 Blackwell Max-Q; decode ctx-0 temp 1. Launch argv transcribed verbatim from the repo's unified Docker guide (same composition). Measured: C1 173.2 tok/s, C8 698.4 tok/s, 32K prefill 12073 tok/s."},"engine_source":{"type":"docker_image","git_url":"https://github.com/local-inference-lab/vllm","base_engine":"vllm","base_version":"karmic-kraken-beta (vLLM cfdecfaa4)","image_digest":"ghcr.io/local-inference-lab/vllm:karmic-kraken-beta-20260922-3221ccacf71002ea","pinned_commit":"cfdecfaa4739ee3141c9745997cd8a83f31745a4"},"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":["serve","local-inference-lab/Qwen3.8-Flash-Next-NVFP4","--async-scheduling","--block-size","64","--compilation-config","'{\"cudagraph_mode\":\"FULL_AND_PIECEWISE\",\"custom_ops\":[\"all\"]}'","--decode-context-parallel-size","1","--dtype","bfloat16","--enable-auto-tool-choice","--enable-chunked-prefill","--no-enable-flashinfer-autotune","--enable-prefix-caching","--enable-prompt-tokens-details","--gdn-decode-kernel","b12x","--gpu-memory-utilization","0.96","--host","0.0.0.0","--kv-cache-dtype","fp8","--no-language-model-only","--linear-backend","b12x","--load-format","instanttensor","--mamba-cache-mode","align","--mamba-ssm-cache-dtype","auto","--max-cudagraph-capture-size","64","--max-model-len","262144","--max-num-batched-tokens","6019","--max-num-seqs","16","--mm-encoder-tp-mode","data","--mm-processor-cache-gb","0.0","--moe-backend","b12x","--pipeline-parallel-size","1","--port","8000","--quantization","modelopt_mixed","--reasoning-parser","qwen3","--served-model-name","Qwen3.8-Flash-Next","--speculative-config","'{\"method\":\"mtp\",\"moe_backend\":\"b12x\",\"num_speculative_tokens\":3}'","--tensor-parallel-size","1","--tool-call-parser","qwen3_xml"],"max_context_len":262144},"models":[{"slug":"qwen3-8-flash-next","name":"Qwen3.8-Flash-Next","hf_repo":"local-inference-lab/Qwen3.8-Flash-Next-NVFP4","quant":"nvfp4"}],"hardware":[{"slug":"nvidia-rtx-pro-6000-blackwell-max-q","vendor":"nvidia","card":"RTX PRO 6000 Blackwell Max-Q","card_family":"rtx-pro-6000-blackwell","vram_gb":96,"device_count":1}],"generation":"blackwell","tags":["mtp3"],"tasks":["chat","code"],"aa":{"aa_index":40,"aa_provenance":"measured","aa_source_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","aa_index_version":"Index v4.3.2","aa_methodology_version":"v4.3.2","aa_published_fetched_at":"2026-10-06 18:30:00-06","aa_family_slug":"qwen3-8-flash-next","aa_resolved_slug":"qwen3-8-flash-next"},"performance":[{"claimed_by":"submitter","metrics":"{\"tok_s\": 173.2}"},{"claimed_by":"submitter","metrics":"{\"notes\": \"Benchmark-qualified medians from local-inference-lab/rtx6kpro (five warmed 30-s windows).\", \"tok_s\": 173.2, \"points\": [{\"notes\": \"Karmic Kraken 5-window median, ctx-0 decode, temp 1 (verifier 81.8 steps/s)\", \"concurrency\": 1, \"context_len\": 1, \"decode_tok_s\": 173.2}, {\"notes\": \"Karmic Kraken 5-window median, ctx-0 decode, temp 1 (verifier 333.7 steps/s)\", \"concurrency\": 8, \"context_len\": 1, \"decode_tok_s\": 698.4}], \"context_len\": 262144}"},{"claimed_by":"submitter","metrics":"[]"}],"perf_points":[{"id":997,"context_len":1,"prefill_tok_s":null,"decode_tok_s":173.19999999999998863131622783839702606201171875,"ttft_ms":null,"concurrency":1,"claimed_by":"submitter","notes":"Karmic Kraken 5-window median, ctx-0 decode, temp 1 (verifier 81.8 steps/s)"},{"id":998,"context_len":1,"prefill_tok_s":null,"decode_tok_s":698.3999999999999772626324556767940521240234375,"ttft_ms":null,"concurrency":8,"claimed_by":"submitter","notes":"Karmic Kraken 5-window median, ctx-0 decode, temp 1 (verifier 333.7 steps/s)"},{"id":999,"context_len":32768,"prefill_tok_s":12073,"decode_tok_s":null,"ttft_ms":null,"concurrency":1,"claimed_by":"submitter","notes":"Karmic Kraken 5-window median, unique uncached nominal-32K requests, client TTFT"}],"agent":{"prompt":"Fetch https://localairecipes.com/api/v1/recipes/qwen3-8-flash-next-1x6000-kk-mtp3.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/qwen3-8-flash-next-1x6000-kk-mtp3.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/qwen3-8-flash-next-1x6000-kk-mtp3.json","alternate":"/r/qwen3-8-flash-next-1x6000-kk-mtp3","describedby":"/openapi.json"},"updated_at":"2026-10-20 15:34:04.148288-06","created_at":"2026-09-28 15:47:09.618563-06","speeds":{"decode_tok_s":173.19999999999998863131622783839702606201171875,"prefill_tok_s":12073,"leaderboard":"/api/v1/leaderboard.json"}}