{"generated_at":"2026-10-31T14:33:07Z","notes":"Boards group by HARDWARE configuration (card family at the same device count; RTX PRO 6000 Max-Q and plain RTX PRO 6000 share a family) \u2014 \"what is the best on this rig\" is the question. Every model with a recipe for that hardware competes together; entries are ranked by the requested ?sort= mode (aa = Artificial Analysis Intelligence of the base model DESC, null/un-scored models last, then C1 single-stream decode per GPU DESC \u2014 the default; decode = C1 decode per GPU DESC; c8 = the exact-C8 decode cell DESC (null-C8 trails, then the C1 decode fallback orders the null-C8 tail); prefill = whole-rig prefill DESC; ttft = TTFT at C1 ASC, lower is better; votes = community vote count DESC (recipe-grain \u2014 votes attach to recipes, one per anon identity); added = recipe creation date DESC, newest first (when it first got listed); updated = last real revision DESC (the same updated_at the recipe twins expose \u2014 a view/vote/import never re-sorts the board); max_context = the recipe's OWN DECLARED max_context_len DESC (t_703c7037 recipe metadata carried on every entry as max_context_len \u2014 NOT a measurement; rows without the declaration sink LAST via null-trail, never first); evidence = measured run file before author-reported) plus a secondary ?then= level applied immediately after the primary (default then=decode, so the default chain is AA intelligence then decode speed) with evidence (measured before reported) and slug as final tiebreaks; board sections and entry order are identical to /leaderboard?sort=<same value> (entry order IS the rank \u2014 there is no rank field). Board SECTION order is hardware-only (generation, family, device count) and never changes with the sort. Boards carry their base model name plus its Artificial Analysis Intelligence index (the quality axis) with aa_index_version/aa_source_url provenance. evidence: reported in the UI for all rows; run-file-backed rows are marked in tooltips (API evidence values: measured = run file on record, reported = author-reported). aa_intelligence is the Artificial Analysis index of the base model (null = not scored); aa_index_version / aa_source_url give the version and page every value was read from. aa_source_url is the source of the EFFECTIVE aa value (measured rows: the recorded page; published rows: the register snapshot_url \u2014 the exact href the HTML AA cell renders; the raw published snapshot also ships as aa_published_source_url). aa is the EFFECTIVE AA value (t_b3adaed5): COALESCE(aa_intelligence, aa_published_index) \u2014 the exact number the HTML AA cell renders and the value sort=aa ranks on. Sorting entries by aa reproduces the page order exactly (null trails, as rendered). PROVENANCE TIERS (aa_provenance field): measured = a locally recorded index in aa_intelligence; published = no local record, the AA-published index is shown instead in aa_published_index with aa_published_methodology_version / aa_published_snapshot_url / aa_published_fetched_at provenance (from the append-only aa_scores register; newest fetched_at wins) \u2014 provenance is descriptive metadata on every row (it is NOT a rank level: a published index ranks by its number like any other), and carries in the number tooltip (the former visible AA published chip is retired for good \u2014 owner, Oct 6); unscored = neither, rendered n/a and trailing (unchanged honest trail).","meta":{"count":4,"sort":"aa","then":"decode","sort_chain":"aa>decode>prefill>evidence>slug","applied":{"hardware":["170hx-x6","170hx-x4","170hx-x3","rtx-3090"]},"origin":"https://localairecipes.com","openapi":"/openapi.json"},"boards":[{"label":"NVIDIA CMP 170HX 64GB \u00d76 (Ampere)","card_family":"170hx","representative_card":"CMP 170HX","vendor":"nvidia","device_count":6,"generation":"ampere","vram_gb":64,"entries":[{"slug":"deepseek-v4-1-flash-sm80-deepinfer-kernel-port-6x-a100-dspark-k5","title":"DeepSeek-V4.1-Flash SM80 DeepInfer kernel port 6x CMP 170HX DSpark K5","url":"/r/deepseek-v4-1-flash-sm80-deepinfer-kernel-port-6x-a100-dspark-k5","beta":false,"base_model":"DeepSeek-V4.1-Flash","aa_intelligence":39,"aa":39,"aa_index_version":"Index v4.3.2","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash","aa_recorded_at":"2026-09-30 22:34:38.86447-06","aa_provenance":"measured","aa_published_index":45,"aa_published_methodology_version":"Index v4.3.2 (2026-10-18)","aa_published_snapshot_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_published_fetched_at":"2026-10-20 21:49:11.309778-06","aa_resolved_slug":"deepseek-v4-1-flash","aa_published_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","card_variant":"cmp-170hx","decode_c1_tok_s":160.80000000000001136868377216160297393798828125,"decode_c4_tok_s":170.5,"decode_c8_tok_s":null,"decode_c16_tok_s":null,"prefill_tok_s":4506.8000000000001818989403545856475830078125,"ttft_ms_c1":10700,"other_concurrencies":[1,4],"max_context_len":1048576,"evidence":"claimed","votes":0}]},{"label":"NVIDIA CMP 170HX 64GB \u00d74 (Ampere)","card_family":"170hx","representative_card":"CMP 170HX","vendor":"nvidia","device_count":4,"generation":"ampere","vram_gb":64,"entries":[{"slug":"deepseek-v4-1-flash-1017-engram-nvme-tp4-pp4-4x-cmp-170hx","title":"DeepSeek-V4.1-Flash-1017 Engram-NVMe TP4/PP4 4x CMP 170HX","url":"/r/deepseek-v4-1-flash-1017-engram-nvme-tp4-pp4-4x-cmp-170hx","beta":false,"base_model":"DeepSeek-V4.1-Flash-1017","aa_intelligence":45,"aa":45,"aa_index_version":"Index v4.3.2 (2026-10-18)","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_recorded_at":"2026-10-19 11:48:38.279934-06","aa_provenance":"measured","aa_published_index":45,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_published_fetched_at":"2026-10-19 12:00:00-06","aa_resolved_slug":"deepseek-v4-1-flash-1017","aa_published_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","card_variant":"cmp-170hx","decode_c1_tok_s":355.69999999999998863131622783839702606201171875,"decode_c4_tok_s":null,"decode_c8_tok_s":867.6000000000000227373675443232059478759765625,"decode_c16_tok_s":null,"prefill_tok_s":2416,"ttft_ms_c1":null,"other_concurrencies":[1,8],"max_context_len":262144,"evidence":"claimed","votes":0},{"slug":"deepseek-v4-1-flash-1017-hybrid-exl3-tp4-4x-cmp-170hx-morrowmake","title":"DeepSeek-V4.1-Flash-1017 Hybrid EXL3 TP4 4x CMP 170HX Morrowmake","url":"/r/deepseek-v4-1-flash-1017-hybrid-exl3-tp4-4x-cmp-170hx-morrowmake","beta":false,"base_model":"DeepSeek-V4.1-Flash-1017","aa_intelligence":45,"aa":45,"aa_index_version":"Index v4.3.2 (2026-10-18)","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_recorded_at":"2026-10-19 11:48:38.279934-06","aa_provenance":"measured","aa_published_index":45,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_published_fetched_at":"2026-10-19 12:00:00-06","aa_resolved_slug":"deepseek-v4-1-flash-1017","aa_published_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","card_variant":"cmp-170hx","decode_c1_tok_s":319,"decode_c4_tok_s":null,"decode_c8_tok_s":765,"decode_c16_tok_s":null,"prefill_tok_s":3818,"ttft_ms_c1":null,"other_concurrencies":[1,8],"max_context_len":262144,"evidence":"claimed","votes":0},{"slug":"deepseek-v4-1-flash-1017-exl3-2-9bpw-tc-moe-on-4x-cmp-170hx-tp4","title":"DeepSeek-V4.1-Flash-1017 EXL3 2.9bpw TC-MoE on 4x CMP 170HX TP4","url":"/r/deepseek-v4-1-flash-1017-exl3-2-9bpw-tc-moe-on-4x-cmp-170hx-tp4","beta":false,"base_model":"DeepSeek-V4.1-Flash-1017","aa_intelligence":45,"aa":45,"aa_index_version":"Index v4.3.2 (2026-10-18)","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_recorded_at":"2026-10-19 11:48:38.279934-06","aa_provenance":"measured","aa_published_index":45,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_published_fetched_at":"2026-10-19 12:00:00-06","aa_resolved_slug":"deepseek-v4-1-flash-1017","aa_published_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","card_variant":"cmp-170hx","decode_c1_tok_s":195.423000000000001818989403545856475830078125,"decode_c4_tok_s":null,"decode_c8_tok_s":276.55000000000001136868377216160297393798828125,"decode_c16_tok_s":null,"prefill_tok_s":1391.09999999999990905052982270717620849609375,"ttft_ms_c1":null,"other_concurrencies":[1,8],"max_context_len":262144,"evidence":"claimed","votes":0},{"slug":"deepseek-v4-1-flash-1017-fidelity-first-4x-cmp-170hx-alanoo81","title":"DeepSeek-V4.1-Flash-1017 Fidelity-First 4x CMP 170HX alanoo81","url":"/r/deepseek-v4-1-flash-1017-fidelity-first-4x-cmp-170hx-alanoo81","beta":false,"base_model":"DeepSeek-V4.1-Flash-1017","aa_intelligence":45,"aa":45,"aa_index_version":"Index v4.3.2 (2026-10-18)","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_recorded_at":"2026-10-19 11:57:39-06","aa_provenance":"measured","aa_published_index":45,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_published_fetched_at":"2026-10-19 12:00:00-06","aa_resolved_slug":"deepseek-v4-1-flash-1017","aa_published_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","card_variant":"cmp-170hx","decode_c1_tok_s":105.400000000000005684341886080801486968994140625,"decode_c4_tok_s":325.19999999999998863131622783839702606201171875,"decode_c8_tok_s":505,"decode_c16_tok_s":null,"prefill_tok_s":2514,"ttft_ms_c1":null,"other_concurrencies":[1,4,8],"max_context_len":262144,"evidence":"claimed","votes":0},{"slug":"glm-5-3-flash-4x170hx-tp4-pp4-morrowmake-141","title":"GLM-5.3-Flash on 4x CMP 170HX \u2014 Morrowmake recipe 1.8.0, TP4 DFlash2","url":"/r/glm-5-3-flash-4x170hx-tp4-pp4-morrowmake-141","beta":false,"base_model":"GLM-5.3-Flash","aa_intelligence":42,"aa":42,"aa_index_version":"Index v4.3.2","aa_source_url":"https://artificialanalysis.ai/models/glm-5-3-flash","aa_recorded_at":"2026-09-30 22:34:38.6629-06","aa_provenance":"measured","aa_published_index":42,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/open-source","aa_published_fetched_at":"2026-10-04 14:15:00-06","aa_resolved_slug":"glm-5-3-flash","aa_published_source_url":"https://artificialanalysis.ai/models/open-source","card_variant":"cmp-170hx","decode_c1_tok_s":264.3999999999999772626324556767940521240234375,"decode_c4_tok_s":null,"decode_c8_tok_s":null,"decode_c16_tok_s":null,"prefill_tok_s":6264,"ttft_ms_c1":63,"other_concurrencies":[1],"max_context_len":262144,"evidence":"measured","votes":1},{"slug":"qwen3-8-flash-next-fp8-4x-cmp-170hx-pp4-mtp-4-patched-vllm-g4bwy","title":"Qwen3.8-Flash-Next-FP8 4x CMP 170HX \u2014 PP4 MTP-4 patched vLLM (g4bwy)","url":"/r/qwen3-8-flash-next-fp8-4x-cmp-170hx-pp4-mtp-4-patched-vllm-g4bwy","beta":false,"base_model":"Qwen3.8-Flash-Next","aa_intelligence":40,"aa":40,"aa_index_version":"Index v4.3.2","aa_source_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","aa_recorded_at":"2026-09-30 22:34:38.764322-06","aa_provenance":"measured","aa_published_index":40,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","aa_published_fetched_at":"2026-10-06 18:30:00-06","aa_resolved_slug":"qwen3-8-flash-next","aa_published_source_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","card_variant":"cmp-170hx","decode_c1_tok_s":184.400000000000005684341886080801486968994140625,"decode_c4_tok_s":548,"decode_c8_tok_s":null,"decode_c16_tok_s":null,"prefill_tok_s":10138,"ttft_ms_c1":91900,"other_concurrencies":[1,4],"max_context_len":1000000,"evidence":"claimed","votes":0},{"slug":"deepseek-v4-1-flash-exl3-3bpw-tc-moe-on-4x-cmp-170hx-tp4","title":"DeepSeek-V4.1-Flash EXL3 3bpw TC-MoE on 4x CMP 170HX TP4 (original checkpoint)","url":"/r/deepseek-v4-1-flash-exl3-3bpw-tc-moe-on-4x-cmp-170hx-tp4","beta":false,"base_model":"DeepSeek-V4.1-Flash","aa_intelligence":39,"aa":39,"aa_index_version":"Index v4.3.2","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash","aa_recorded_at":"2026-09-30 22:34:38.86447-06","aa_provenance":"measured","aa_published_index":45,"aa_published_methodology_version":"Index v4.3.2 (2026-10-18)","aa_published_snapshot_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_published_fetched_at":"2026-10-20 21:49:11.309778-06","aa_resolved_slug":"deepseek-v4-1-flash","aa_published_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","card_variant":"cmp-170hx","decode_c1_tok_s":178.80000000000001136868377216160297393798828125,"decode_c4_tok_s":343.8999999999999772626324556767940521240234375,"decode_c8_tok_s":586.6000000000000227373675443232059478759765625,"decode_c16_tok_s":null,"prefill_tok_s":1570,"ttft_ms_c1":null,"other_concurrencies":[1,4,8],"max_context_len":262144,"evidence":"claimed","votes":0},{"slug":"deepseek-v4-1-flash-764b-on-4x-cmp-170hx-pp4-shadow-kv-exl3-2bpw","title":"DeepSeek-V4.1-Flash (764B) on 4x CMP 170HX \u2014 PP4, shadow KV, EXL3 2bpw, DSpark K5, 512k ctx, native vision (kaka86mm)","url":"/r/deepseek-v4-1-flash-764b-on-4x-cmp-170hx-pp4-shadow-kv-exl3-2bpw","beta":false,"base_model":"DeepSeek-V4.1-Flash","aa_intelligence":39,"aa":39,"aa_index_version":"Index v4.3.2","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash","aa_recorded_at":"2026-09-30 22:34:38.86447-06","aa_provenance":"measured","aa_published_index":45,"aa_published_methodology_version":"Index v4.3.2 (2026-10-18)","aa_published_snapshot_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","aa_published_fetched_at":"2026-10-20 21:49:11.309778-06","aa_resolved_slug":"deepseek-v4-1-flash","aa_published_source_url":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","card_variant":"cmp-170hx","decode_c1_tok_s":60.7000000000000028421709430404007434844970703125,"decode_c4_tok_s":null,"decode_c8_tok_s":200.599999999999994315658113919198513031005859375,"decode_c16_tok_s":null,"prefill_tok_s":null,"ttft_ms_c1":null,"other_concurrencies":[1,8,24],"max_context_len":524288,"evidence":"claimed","votes":0},{"slug":"mimo-v2-6-flash-rl-309b-moe-nvfp4-4x-cmp-170hx-tp4-dflash-1m-ctx","title":"MiMo-V2.6-Flash-RL 309B MoE NVFP4 4x CMP 170HX TP4 DFlash 1M ctx (ElectroHobo)","url":"/r/mimo-v2-6-flash-rl-309b-moe-nvfp4-4x-cmp-170hx-tp4-dflash-1m-ctx","beta":false,"base_model":"MiMo-V2.6-Flash-RL","aa_intelligence":null,"aa":38,"aa_index_version":null,"aa_source_url":"https://artificialanalysis.ai/models/mimo-v2-6-flash","aa_recorded_at":"2026-10-06 17:02:43.626846-06","aa_provenance":"published","aa_published_index":38,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/mimo-v2-6-flash","aa_published_fetched_at":"2026-10-06 18:15:00-06","aa_resolved_slug":"mimo-v2-6-flash","aa_published_source_url":"https://artificialanalysis.ai/models/mimo-v2-6-flash","card_variant":"cmp-170hx","decode_c1_tok_s":322,"decode_c4_tok_s":null,"decode_c8_tok_s":753.799999999999954525264911353588104248046875,"decode_c16_tok_s":null,"prefill_tok_s":2722,"ttft_ms_c1":null,"other_concurrencies":[1,8],"max_context_len":1048576,"evidence":"claimed","votes":0},{"slug":"mimo-v2-6-flash-rl-omni-on-4x-cmp-170hx-pp4-official-fp8-three-t","title":"MiMo-V2.6-Flash-RL (omni) on 4x CMP 170HX \u2014 PP4, official fp8, three-tier KV, v3.3 (kaka86mm)","url":"/r/mimo-v2-6-flash-rl-omni-on-4x-cmp-170hx-pp4-official-fp8-three-t","beta":false,"base_model":"MiMo-V2.6-Flash-RL","aa_intelligence":null,"aa":38,"aa_index_version":null,"aa_source_url":"https://artificialanalysis.ai/models/mimo-v2-6-flash","aa_recorded_at":"2026-10-06 17:02:43.626846-06","aa_provenance":"published","aa_published_index":38,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/mimo-v2-6-flash","aa_published_fetched_at":"2026-10-06 18:15:00-06","aa_resolved_slug":"mimo-v2-6-flash","aa_published_source_url":"https://artificialanalysis.ai/models/mimo-v2-6-flash","card_variant":"cmp-170hx","decode_c1_tok_s":64.5,"decode_c4_tok_s":null,"decode_c8_tok_s":null,"decode_c16_tok_s":483,"prefill_tok_s":6050,"ttft_ms_c1":3300,"other_concurrencies":[1,16,32],"max_context_len":1048576,"evidence":"claimed","votes":0}]},{"label":"NVIDIA CMP 170HX 64GB \u00d73 (Ampere)","card_family":"170hx","representative_card":"CMP 170HX","vendor":"nvidia","device_count":3,"generation":"ampere","vram_gb":64,"entries":[{"slug":"qwen3-8-flash-next-w4a16-3x-cmp-170hx-pp3-nvme-ple-fp8-kv-1m-cle","title":"Qwen3.8-Flash-Next W4A16 3x CMP 170HX PP3 NVMe PLE fp8 KV 1M (clee)","url":"/r/qwen3-8-flash-next-w4a16-3x-cmp-170hx-pp3-nvme-ple-fp8-kv-1m-cle","beta":false,"base_model":"Qwen3.8-Flash-Next","aa_intelligence":40,"aa":40,"aa_index_version":"Index v4.3.2","aa_source_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","aa_recorded_at":"2026-09-30 22:34:38.764322-06","aa_provenance":"measured","aa_published_index":40,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","aa_published_fetched_at":"2026-10-06 18:30:00-06","aa_resolved_slug":"qwen3-8-flash-next","aa_published_source_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","card_variant":"cmp-170hx","decode_c1_tok_s":74.900000000000005684341886080801486968994140625,"decode_c4_tok_s":null,"decode_c8_tok_s":null,"decode_c16_tok_s":null,"prefill_tok_s":4690,"ttft_ms_c1":223000,"other_concurrencies":[1],"max_context_len":1048576,"evidence":"claimed","votes":1},{"slug":"ds4-flash-3x170hx-pp3-dspark-k5","title":"DeepSeek V4 Flash-0731 abliterated on 3x CMP 170HX \u2014 vLLM patched PP3 DSpark K5","url":"/r/ds4-flash-3x170hx-pp3-dspark-k5","beta":false,"base_model":"DeepSeek-V4-Flash-0731","aa_intelligence":34,"aa":34,"aa_index_version":"Index v4.3.2","aa_source_url":"https://artificialanalysis.ai/models/deepseek-v4-flash","aa_recorded_at":"2026-09-30 22:34:38.962437-06","aa_provenance":"measured","aa_published_index":34,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/deepseek-v4-flash","aa_published_fetched_at":"2026-10-07 18:00:00-06","aa_resolved_slug":"deepseek-v4-flash-0731","aa_published_source_url":"https://artificialanalysis.ai/models/deepseek-v4-flash","card_variant":"cmp-170hx","decode_c1_tok_s":181,"decode_c4_tok_s":null,"decode_c8_tok_s":null,"decode_c16_tok_s":null,"prefill_tok_s":2350,"ttft_ms_c1":null,"other_concurrencies":[1],"max_context_len":262144,"evidence":"claimed","votes":0}]},{"label":"NVIDIA RTX 3090 24GB \u00d71 (Ampere)","card_family":"rtx-3090","representative_card":"RTX 3090","vendor":"nvidia","device_count":1,"generation":"ampere","vram_gb":24,"entries":[{"slug":"glm-5-3-flash-exl3-3-05bpw-on-1x-rtx-3090-ram-nvme-expert-tierin","title":"GLM-5.3-Flash EXL3 3.05bpw on 1x RTX 3090 \u2014 RAM/NVMe expert tiering (near-exact)","url":"/r/glm-5-3-flash-exl3-3-05bpw-on-1x-rtx-3090-ram-nvme-expert-tierin","beta":false,"base_model":"GLM-5.3-Flash","aa_intelligence":42,"aa":42,"aa_index_version":"Index v4.3.2","aa_source_url":"https://artificialanalysis.ai/models/glm-5-3-flash","aa_recorded_at":"2026-09-30 22:34:38.6629-06","aa_provenance":"measured","aa_published_index":42,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/open-source","aa_published_fetched_at":"2026-10-04 14:15:00-06","aa_resolved_slug":"glm-5-3-flash","aa_published_source_url":"https://artificialanalysis.ai/models/open-source","card_variant":"RTX 3090","decode_c1_tok_s":28.14999999999999857891452847979962825775146484375,"decode_c4_tok_s":null,"decode_c8_tok_s":null,"decode_c16_tok_s":null,"prefill_tok_s":1015,"ttft_ms_c1":null,"other_concurrencies":[1],"max_context_len":null,"evidence":"claimed","votes":0},{"slug":"qwen3-8-flash-next-w4a16-fp8ple-on-1x-rtx-3090-cpu-cold-experts","title":"Qwen3.8-Flash-Next W4A16-FP8PLE on 1x RTX 3090 \u2014 CPU cold experts, MTP3, 128K (DominikBucko)","url":"/r/qwen3-8-flash-next-w4a16-fp8ple-on-1x-rtx-3090-cpu-cold-experts","beta":false,"base_model":"Qwen3.8-Flash-Next","aa_intelligence":40,"aa":40,"aa_index_version":"Index v4.3.2","aa_source_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","aa_recorded_at":"2026-09-30 22:34:38.764322-06","aa_provenance":"measured","aa_published_index":40,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","aa_published_fetched_at":"2026-10-06 18:30:00-06","aa_resolved_slug":"qwen3-8-flash-next","aa_published_source_url":"https://artificialanalysis.ai/models/qwen3-8-flash-next","card_variant":"RTX 3090","decode_c1_tok_s":50.2999999999999971578290569595992565155029296875,"decode_c4_tok_s":null,"decode_c8_tok_s":null,"decode_c16_tok_s":null,"prefill_tok_s":2141,"ttft_ms_c1":62200,"other_concurrencies":[1],"max_context_len":135168,"evidence":"claimed","votes":0},{"slug":"qwen3-8-27b-awq-int4-dspark-on-rtx-3090s-sglang-tp1-tp2-tp4","title":"Qwen3.8-27B AWQ-INT4 + DSpark on RTX 3090s \u2014 SGLang TP1/TP2/TP4","url":"/r/qwen3-8-27b-awq-int4-dspark-on-rtx-3090s-sglang-tp1-tp2-tp4","beta":false,"base_model":"Qwen3.8-27B","aa_intelligence":null,"aa":34,"aa_index_version":null,"aa_source_url":"https://artificialanalysis.ai/models/qwen3-8-27b","aa_recorded_at":null,"aa_provenance":"published","aa_published_index":34,"aa_published_methodology_version":"v4.3.2","aa_published_snapshot_url":"https://artificialanalysis.ai/models/qwen3-8-27b","aa_published_fetched_at":"2026-10-07 18:00:00-06","aa_resolved_slug":"qwen-3-8-27b","aa_published_source_url":"https://artificialanalysis.ai/models/qwen3-8-27b","card_variant":"RTX 3090","decode_c1_tok_s":136.80000000000001136868377216160297393798828125,"decode_c4_tok_s":103.7999999999999971578290569595992565155029296875,"decode_c8_tok_s":60.5,"decode_c16_tok_s":null,"prefill_tok_s":1615.799999999999954525264911353588104248046875,"ttft_ms_c1":98880,"other_concurrencies":[1,4,8],"max_context_len":null,"evidence":"claimed","votes":0}]}]}