{"meta":{"count":3,"page":1,"pages":1,"per_page":12,"applied":{"engine":null,"model":null,"quant":null,"storage":null,"hardware":"rtx-pro-6000-blackwell-x4","generation":null,"task":null,"tier":null,"tags":[],"vram":null,"search":null,"sort":"updated","featured":false},"origin":"https://localairecipes.com","openapi":"/openapi.json","updated_at":"2026-10-31T20:04:27+00:00"},"recipes":[{"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.","tier":"community","beta":false,"generation":"blackwell","decode_tok_s":248.900000000000005684341886080801486968994140625,"prefill_tok_s":13514,"updated_at":"2026-10-20 21:54:52.705261-06","commit_sha":"6dd7e5b0fb0df423b2756f568d4857e6559037a5","content_hash":"02ec2981d8b12da82eab3f9dc57cd9652c2b1e75","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/glm-5-3-flash-4x6000-jj-mtp3.json","alternate":"/r/glm-5-3-flash-4x6000-jj-mtp3"}},{"slug":"glm-5-3-flash-4x6000-jj-dflash2-k7","title":"GLM-5.3-Flash on 4x RTX PRO 6000 Blackwell \\x{2014} TP4 DFlash2 K7","summary":"Community image TP4 serving recipe: DFlash2 K7 offline-MXFP8 draft, B12X MoE, FP8 KV, 1M context. Saved five-window medians (Max-Q +6000).","tier":"community","beta":false,"generation":"blackwell","decode_tok_s":219.69999999999998863131622783839702606201171875,"prefill_tok_s":13840,"updated_at":"2026-10-20 21:54:52.681322-06","commit_sha":"e67bce0bc6689f5df94be561cf643f978e0b5efc","content_hash":"9378ba12c7d0655e1eda733d5c9983d7e5b325bc","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/glm-5-3-flash-4x6000-jj-dflash2-k7.json","alternate":"/r/glm-5-3-flash-4x6000-jj-dflash2-k7"}},{"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.","tier":"community","beta":false,"generation":"blackwell","decode_tok_s":230.599999999999994315658113919198513031005859375,"prefill_tok_s":17503,"updated_at":"2026-10-20 21:54:52.540452-06","commit_sha":"218c00c639d52ad29638628a64740ea90069ffe1","content_hash":"77484355ac2ebdc80317b43b37868302df70cf22","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/ds4-1-flash-4x6000-jj-dspark-k7.json","alternate":"/r/ds4-1-flash-4x6000-jj-dspark-k7"}}]}