{"schema":"sb.node.v1","id":"sb:e/439e9085c1f9105c3ad7cdcc","kind":"entity","label":{"text":"vram","locale":"en"},"identity":{"anchor":"label:en:vram","strength":"label"},"asOf":{"knowledgeCutoff":"2026-10-08T23:32:17.032179+00:00","snapshot":"deploy 0883c9630a8613ed84fd63507671bc4104b77b63"},"lens":{"kind":"public"},"build":{"plane":"projected","builtFrom":["entity_graph.slim.json","entity_receipts (deploy asset)","event_graph.json","truth_records (deploy asset)","corroborated_record.json"],"rule":"node-projection.entity@v1"},"standing":{"evidence":{"supporting":57,"separatePublishers":17,"basis":"documents that mention the subject and the outlets that carried them; a mention is evidence the referent is in use, not evidence about any claim"},"admission":{"state":"canonical","reason":"entity graph provenance 'curated'; the node carries no promotion receipt in v1","policy":"EQ-PROMOTION (receipt not carried)"},"disposition":{"state":"served","reason":"public record"},"validity":{"from":"2026-08-03","to":"2026-10-07","basis":"first and last day we saw it mentioned; not the subject's own lifetime"},"measurement":{"state":"partial","blind":["assertion coverage 0.14: about 86% of mentions carry no typed assertion"]}},"dimensions":{"domains":["auto","artificial_intelligence","semiconductors"],"activeDays":27,"assertions":{}},"up":[],"upNote":"An entity is a root: it is contained by nothing. Pan out by following R.","children":{"count":12,"byKind":{"observation":12},"items":[{"id":"sb:o/a6f832efcaf61cd69344075b","kind":"observation","label":"Wccftech · 2026-10-03 · GIGABYTE AI TOP 100 B850 Doubles RTX 5090’s VRAM With Dual Radeon AI PRO R9700 GPUs, Handling 235B-Parameter Inference","url":"https://wccftech.com/gigabyte-launches-ai-top-100-b850-desktop/"},{"id":"sb:o/8bb4833d652a8183e9d39c8d","kind":"observation","label":"Geeky Gadgets · 2026-09-28 · MSI Pro Max Edge AI+ Packs a Radeon 8060S with 96GB VRAM","url":"https://www.geeky-gadgets.com/msi-pro-max-edge-ai-plus/"},{"id":"sb:o/f92bf2714ac9bd6245952610","kind":"observation","label":"Tom's Hardware · 2026-09-09 · Nvidia's unreleased RTX 3070 Ti 16GB comes to life thanks to a modder's crazy GDDR6 swap — Frankenstein card combines RTX 3070 PCB and new VRAM with RTX 3070 Ti GPU","url":"https://www.tomshardware.com/pc-components/gpus/nvidias-unreleased-rtx-3070-ti-16gb-comes-to-life-thanks-to-a-modders-crazy-gddr6-swap-frankenstein-card-combines-rtx-3070-pcb-and-new-vram-with-rtx-3070-ti-gpu"},{"id":"sb:o/9605e7ea1f3a404a5dace732","kind":"observation","label":"Latest from Tom's Hardware · 2026-10-07 · This monster RTX 5090 Alienware gaming PC costs less than buying the GPU and CPU alone","url":"https://www.tomshardware.com/desktops/gaming-pcs/this-monster-rtx-5090-alienware-gaming-pc-costs-less-than-buying-the-gpu-and-cpu-alone-take-usd500-off-a-powerful-9950x3d-rig"},{"id":"sb:o/c822fee99ceaefb43fdd8931","kind":"observation","label":"shattered.io · 2026-10-07 · Sony’s QSSR AI Upscaler Hits 2 Base PS5 Games [2026]","url":"https://shattered.io/sony-qssr-ai-upscaler-base-ps5-2026/"},{"id":"sb:o/092ea1bb629f40fc89f59931","kind":"observation","label":"shattered.io · 2026-10-07 · AMD Claims 500K Agentic PCs Shipped Before RTX Spark [2026]","url":"https://shattered.io/amd-500k-agentic-pcs-shipped-before-rtx-spark-2026/"},{"id":"sb:o/95150ca43037a8c6d2f4bbaa","kind":"observation","label":"Wccftech · 2026-10-06 · The Witcher 3: Wild Hunt — Remastered PC Performance Analysis & Tuning Guide – How To Get The Best Experience On PC","url":"https://wccftech.com/how-to/the-witcher-3-wild-hunt-remastered-pc-performance-analysis-tuning-guide-how-to-get-the-best-experience-on-pc/"},{"id":"sb:o/7044471bb71dacbed8bb4a6f","kind":"observation","label":"Tech Times · 2026-10-06 · ASRock DeskSlim Brings RTX Pro Blackwell GPU Support to Compact Desktop","url":"https://www.techtimes.com/articles/328613/20261006/asrock-deskslim-brings-rtx-pro-blackwell-gpu-support-compact-desktop.htm"},{"id":"sb:o/afde1506b813eb19f93c6af7","kind":"observation","label":"shattered.io · 2026-10-06 · AMD Gorgon Halo Benchmarks Hit Back at RTX Spark [2026]","url":"https://shattered.io/amd-gorgon-halo-benchmarks-vs-rtx-spark-2026/"},{"id":"sb:o/668b52bbc7f45d0b47d003c4","kind":"observation","label":"Hacker News Top Stories · 2026-10-04 · Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s","url":"https://github.com/Niko1221/Strata"}],"cursor":"c1.eyJpZCI6InNiOmUvNDM5ZTkwODVjMWY5MTA1YzNhZDdjZGNjIiwibCI6ImNoaWxkcmVuIiwibyI6MTAsImsiOm51bGwsImEiOiIyMDI2LTEwLTA4VDIzOjMyOjE3LjAzMjE3OSswMDowMCJ9","order":"newest first; we keep the 12 newest receipts for this entity. Its other observations are counted in standing.evidence.supporting but are not addressable in v1"},"relations":{"count":10,"byKind":{"co-mentioned":10},"items":[{"kind":"relation","label":"co-mentioned with ai (46 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/456e3610e32e4aa8fa93c161"},{"kind":"relation","label":"co-mentioned with nvidia (43 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/5ac81af383fb86bc4bff3e7d"},{"kind":"relation","label":"co-mentioned with rtx (37 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/26a243ff3a68c25a99e09625"},{"kind":"relation","label":"co-mentioned with gpus (32 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/cdce84a27657b096ac6f7e66"},{"kind":"relation","label":"co-mentioned with amd (30 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/138a61f9f98e35f059664f80"},{"kind":"relation","label":"co-mentioned with size (26 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/b17b704235c25e062aaa6c41"},{"kind":"relation","label":"co-mentioned with google (25 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/04faf7468114640031f0fd74"},{"kind":"relation","label":"co-mentioned with buy (24 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/50af316636d86fd7eb04ce34"},{"kind":"relation","label":"co-mentioned with intel (23 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/146f2ce83ccd68be90f1c052"},{"kind":"relation","label":"co-mentioned with qwen (15 documents)","role":"co-mentioned","relationKind":"co-mentioned","members":2,"id":"sb:r/126bd91eccc65fdd7dbee480"}],"cursor":null,"order":"situations first, then claims (the subject's own maintained record, then site-wide corroborated clusters; each label ends with its standing), then co-mentions by shared documents, descending. Co-mentions are the ten strongest the entity graph keeps per entity"},"edge":{"state":"continues"},"links":{"rest":"/api/v1/node/e/439e9085c1f9105c3ad7cdcc","mcp":"traverse {\"id\":\"sb:e/439e9085c1f9105c3ad7cdcc\"}","page":"/entity/vram/"},"limits":{"levelsPerCall":1,"pageSize":10,"maxPageSize":50,"membersMax":50,"statement":"One level per call: depth is 1 and only 1, and there is no whole-graph dump. pageSize 1-50 (default 10); a page limit is a cursor, never an edge. Members are listed up to 50. At most 60 traverse calls a minute per caller (runaway-loop protection, not a meter). One knowledge cutoff is served: the deploy's."},"actions":[{"verb":"unfold","lit":true,"effect":"read","layer":"cantina","call":"traverse {\"id\":\"sb:e/439e9085c1f9105c3ad7cdcc\",\"level\":\"children\"}"},{"verb":"fold","lit":true,"effect":"read","layer":"cantina","call":"traverse {\"id\":\"sb:e/439e9085c1f9105c3ad7cdcc\"}"},{"verb":"panOut","lit":false,"effect":"read","layer":"cantina","reason":"An entity is a root: it is contained by nothing. Pan out by following R."},{"verb":"follow","lit":true,"effect":"read","layer":"cantina","call":"traverse {\"id\":\"sb:e/439e9085c1f9105c3ad7cdcc\",\"level\":\"relations\"}"},{"verb":"receipts","lit":false,"effect":"read","layer":"cantina","reason":"receipts are the observations below this node; unfold to reach them"},{"verb":"edge","lit":true,"effect":"read","layer":"cantina","call":"traverse {\"id\":\"sb:e/439e9085c1f9105c3ad7cdcc\"}"},{"verb":"asOf","lit":false,"effect":"read","layer":"cantina","reason":"v1 serves one knowledge cutoff, this deploy's; walking an earlier cutoff needs retained history (EQ-REPLAY), which v1 does not keep"},{"verb":"switchObserver","lit":false,"effect":"read","layer":"cantina","reason":"the public record is the same for every observer; traversal through a Watch's lens is not served in v1"},{"verb":"readOriginal","lit":false,"effect":"read","layer":"cantina","reason":"no translation is applied on this node; every label is the source's own text"},{"verb":"save","lit":false,"effect":"watch-declaration","layer":"workshop","reason":"saving applies to a configured Watch; configure one around this node first (free), then save it"},{"verb":"deliver","lit":false,"effect":"watch-declaration","layer":"workshop","reason":"delivery applies to a saved Watch"},{"verb":"format","lit":false,"effect":"watch-declaration","layer":"workshop","reason":"output format applies to a saved Watch"},{"verb":"deltaR","lit":false,"effect":"read","layer":"workshop","reason":"Delta R needs a saved Watch with a previous reading"},{"verb":"read","lit":false,"effect":"read","layer":"docking-bay","reason":"one-time Reads are parked until the Commander decides their shape (#938)"}]}