{"slug":"glm-5-3-flash-4x6000-jj-mtp3","title":"GLM-5.3-Flash on 4x RTX PRO 6000 Blackwell \\x{2014} TP4 MTP3","summary":"Community image TP4 serving recipe: MTP3 draft, B12X MoE, FP8 KV, 1M context. Saved five-window medians (Max-Q +6000), the reference the Karmic Kraken report compares against.","license":"CC-BY-4.0","tier":"community","beta":false,"revision":{"no":2,"commit_sha":"6dd7e5b0fb0df423b2756f568d4857e6559037a5","content_hash":"02ec2981d8b12da82eab3f9dc57cd9652c2b1e75","created_at":"2026-10-20 21:54:52.705261-06","notes":"Saved r35 numbers from the Karmic Kraken comparison table (same-box Max-Q +6000 conditions). Launch argv transcribed from the r35 community deployment page (docker run, TP4/DCP1, GPU_MEM 0.93, fp8_ds_mla KV)."},"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 r35 (community)","image_digest":"localinferencelab/vllm:jovian-judgement-community-20260911-r35","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","run","-d","--init","--network","host","--ipc","host","-v","jovian-judgement-r33-runtime-cache:/cache","-v","jovian-judgement-huggingface-cache:/root/.cache/huggingface","-e","MODEL=local-inference-lab/GLM-5.3-Flash-NVFP4","-e","CACHE_MODE=vram","-e","KV_CACHE_QUANT=fp8_ds_mla","-e","TP=4","-e","DCP=1","-e","PORT=8000","-e","MAX_MODEL_LEN=1048576","-e","MAX_NUM_SEQS=32","-e","MAX_NUM_BATCHED_TOKENS=4096","-e","PREFILL_SCHEDULE_INTERVAL=1","-e","PREFILL_COMPUTE_SHARE=0.4","-e","GPU_MEMORY_UTILIZATION=0.93","-e","SPECULATOR=mtp","-e","MTP_DEPTH=3","localinferencelab/vllm:jovian-judgement-community-20260911-r35"],"max_context_len":1048576},"models":[{"slug":"glm-5-3-flash","name":"GLM-5.3-Flash","hf_repo":"local-inference-lab/GLM-5.3-Flash-NVFP4","quant":"nvfp4"}],"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":["jovian-judgement","mtp3"],"tasks":["chat","code"],"aa":{"aa_index":42,"aa_provenance":"measured","aa_source_url":"https://artificialanalysis.ai/models/glm-5-3-flash","aa_index_version":"Index v4.3.2","aa_methodology_version":"v4.3.2","aa_published_fetched_at":"2026-10-04 14:15:00-06","aa_family_slug":"glm-5-3-flash","aa_resolved_slug":"glm-5-3-flash"},"performance":[{"claimed_by":"submitter","metrics":"{\"points\": [{\"notes\": \"Saved JJ reference, 5-window median, ctx-0 decode, temp 1/top-p .95 (verifier 99.4 steps/s)\", \"concurrency\": 1, \"context_len\": 1, \"decode_tok_s\": 248.900000000000005684341886080801486968994140625}, {\"notes\": \"Saved JJ reference, aggregate C8 (verifier 351.9 steps/s)\", \"concurrency\": 8, \"context_len\": 1, \"decode_tok_s\": 873.799999999999954525264911353588104248046875}, {\"notes\": \"Saved JJ reference, uncached nominal-32K prefill, client TTFT\", \"concurrency\": 1, \"context_len\": 32768, \"prefill_tok_s\": 13514}]}"}],"perf_points":[{"id":1744,"context_len":1,"prefill_tok_s":null,"decode_tok_s":248.900000000000005684341886080801486968994140625,"ttft_ms":null,"concurrency":1,"claimed_by":"submitter","notes":"Saved JJ reference, 5-window median, ctx-0 decode, temp 1/top-p .95 (verifier 99.4 steps/s)"},{"id":1745,"context_len":1,"prefill_tok_s":null,"decode_tok_s":873.799999999999954525264911353588104248046875,"ttft_ms":null,"concurrency":8,"claimed_by":"submitter","notes":"Saved JJ reference, aggregate C8 (verifier 351.9 steps/s)"},{"id":1746,"context_len":32768,"prefill_tok_s":13514,"decode_tok_s":null,"ttft_ms":null,"concurrency":1,"claimed_by":"submitter","notes":"Saved JJ reference, uncached nominal-32K prefill, client TTFT"}],"agent":{"prompt":"Fetch https://localairecipes.com/api/v1/recipes/glm-5-3-flash-4x6000-jj-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/glm-5-3-flash-4x6000-jj-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/glm-5-3-flash-4x6000-jj-mtp3.json","alternate":"/r/glm-5-3-flash-4x6000-jj-mtp3","describedby":"/openapi.json"},"updated_at":"2026-10-20 21:54:52.705261-06","created_at":"2026-10-20 21:49:13.564419-06","speeds":{"decode_tok_s":248.900000000000005684341886080801486968994140625,"prefill_tok_s":13514,"leaderboard":"/api/v1/leaderboard.json"}}