{"meta":{"count":3,"page":1,"pages":1,"per_page":12,"applied":{"engine":null,"model":null,"quant":null,"storage":null,"hardware":"rtx-pro-6000-blackwell-x2","generation":null,"task":null,"tier":null,"tags":[],"vram":null,"search":null,"sort":"updated","featured":false},"origin":"https://localairecipes.com","openapi":"/openapi.json","updated_at":"2026-10-31T06:35:58+00:00"},"recipes":[{"slug":"ds4-vision-2x6000-jj-dspark-k3","title":"DeepSeek V4 Flash Vision on 2x RTX PRO 6000 Blackwell \\x{2014} TP2 DSpark K3","summary":"Community image TP2 DSpark K3 Vision serving recipe: B12X sparse MoE, FP8 KV, three draft layers, 1M context. Saved numbers from the KK comparison.","tier":"community","beta":false,"generation":"blackwell","decode_tok_s":169.19999999999998863131622783839702606201171875,"prefill_tok_s":8993,"updated_at":"2026-10-20 21:54:52.636866-06","commit_sha":"17fd5669c2c9eaeb55ffb611f348686755997213","content_hash":"a67645b428d443142e2632eb2d7b7ff2eb8c27c4","votes":0,"credit":[{"name":"local-inference-lab","url":"https://github.com/local-inference-lab/rtx6kpro"}],"uploaded_by":"localai-recipes","measured":null,"links":{"self":"/api/v1/recipes/ds4-vision-2x6000-jj-dspark-k3.json","alternate":"/r/ds4-vision-2x6000-jj-dspark-k3"}},{"slug":"ds4-flash-2x6000-jj-dspark-k5","title":"DeepSeek V4 Flash-0731 on 2x RTX PRO 6000 Blackwell \\x{2014} TP2 DSpark K5","summary":"Community image TP2 DSpark K5 serving recipe: B12X sparse MoE, FP8 KV, InstantTensor loading, 1M context. Saved numbers from the KK comparison (Max-Q +6000).","tier":"community","beta":false,"generation":"blackwell","decode_tok_s":214.900000000000005684341886080801486968994140625,"prefill_tok_s":11167,"updated_at":"2026-10-20 21:54:52.587962-06","commit_sha":"aa77cf295a865cd2380aa3150da706889728140b","content_hash":"655e2c0c651bd72eb6a493c12824a232b005a10c","votes":0,"credit":[{"name":"local-inference-lab","url":"https://github.com/local-inference-lab/rtx6kpro"}],"uploaded_by":"localai-recipes","measured":null,"links":{"self":"/api/v1/recipes/ds4-flash-2x6000-jj-dspark-k5.json","alternate":"/r/ds4-flash-2x6000-jj-dspark-k5"}},{"slug":"glm-5-3-flash-qad-csf-on-2x-rtx-pro-6000-blackwell-tp2-dcp2-mtp3","title":"GLM-5.3-Flash QAD (CSF) on 2x RTX PRO 6000 Blackwell \u2014 TP2/DCP2 MTP3","summary":"Local Inference Lab production two-card serving config: TP2/DCP2, 8 concurrent seqs, MTP3 on B12X, lossless-CSF NVFP4 MoE (MXFP8-CSF-QAD weights, 188.87 GB), online MXFP8 attention and shared experts, NVFP4 MTP experts, FP8 KV, host embeddings, MXFP8 vision, 1,048,576 context at 0.985 GPU memory. Reported KV pool 2,053,877 tokens at 0.984 memory with the 4096-token batch budget; guild-benchmarked at 207/488/672 tok/s at 1/4/8 users, about 68% of the 4-card TP4 reference on the same checkpoint.","tier":"community","beta":false,"generation":"blackwell","decode_tok_s":207,"prefill_tok_s":0,"updated_at":"2026-10-20 15:34:06.136201-06","commit_sha":"379e6111fef42f62bf472d1b559f4514dd06c1b6","content_hash":"fc89c71f949991e16656968e86cdcababa686f4a","votes":0,"credit":[{"name":"local-inference-lab","url":"https://github.com/local-inference-lab/blackwell-llm-docker"}],"uploaded_by":"localai-recipes","measured":null,"links":{"self":"/api/v1/recipes/glm-5-3-flash-qad-csf-on-2x-rtx-pro-6000-blackwell-tp2-dcp2-mtp3.json","alternate":"/r/glm-5-3-flash-qad-csf-on-2x-rtx-pro-6000-blackwell-tp2-dcp2-mtp3"}}]}