The GRID VCA BASE has 8 Kepler GPUs (4GB each), 16 CPU threads and 192 GB memory; the MAX has 16 GPUs, 32 threads and 384 GB.
Mostly true True in substance, wrong in a detail.
Factual: Statements about the present or the past, checked against the record: did they hold up?
The second judge would not resolve this claim; the verdict shown is the first judge's.
Said for an organisation they lead or work for; it counts on both records.
What would count as true or false
Compare the claim with NVIDIA's published GRID VCA specifications from the time of launch (GTC, March 2013). The claim has six figures: BASE has 8 Kepler GPUs with 4 GB of framebuffer each, 16 CPU threads and 192 GB of system memory; MAX has 16 GPUs, 32 threads and 384 GB. True: all six figures and the 4 GB-per-GPU framebuffer match the official spec sheet or launch announcement. Mostly true: everything matches except one minor detail, such as the framebuffer being described differently or one secondary figure being slightly off. Mixed: about half of the figures match. Mostly false: most figures are wrong, but the two-tier BASE/MAX configuration really existed. False: the official specs contradict the figures outright, or the configurations did not exist. If NVIDIA formally revised the specs before shipping, the revised specs govern.
Set before the research began.
Evidence (3)
-
E1 NVIDIA GPU Tech Conference report - fxguide fxguide · 20 March 2013
“8 GPU system with 16 threads of Xeon CPU and 192GB of system RAM ($24,900 + $2,400/year for software license).”
-
E2 NVIDIA GPU Tech Conference report - fxguide fxguide · 20 March 2013
“16 GPU system with 32 threads of Xeon CPU and 384GB of system RAM ($39,900 + $4,800/year for software license)”
-
E3 NVIDIA Unveils Industry's First Visual Computing Appliance NVIDIA · 19 March 2013 Own record
“Available in the United States in May from authorized value-added resellers, NVIDIA GRID VCA is offered in 8 GPU or 16 GPU configurations, with pricing starting at $24,900, plus an annual software license of $2,400.”
Reasoning
fxguide's independent GTC 2013 report describes an 8-GPU GRID VCA with 16 Xeon CPU threads and 192GB of system RAM (E2), and a 16-GPU system with 32 threads and 384GB (E3). That matches all six configuration figures in the claim. NVIDIA's launch release confirms the 8-GPU and 16-GPU configurations (E4). None of the evidence confirms the 4GB framebuffer per GPU or the BASE/MAX names, so the claim is rated mostly true rather than fully true.
Cite this claim
Jensen Huang, “The GRID VCA BASE has 8 Kepler GPUs (4GB each), 16 CPU threads and 192 GB memory; the MAX has 16 GPUs, 32 threads and 384 GB.” (said March 2013). Verdict: mostly true. Reliability API, claim c_f73742167f0d, method 0.1.0+03d23c0e, dataset release v1.1.2. https://epistacklabs.com/claims/c_f73742167f0d
This claim is in dataset release v1.1.2, with the same verdict.
Reply to this claim
More factual claims by Jensen Huang
-
Mostly true
“our architecture is fungible in the sense that it runs every AI model, runs all data processing and parallel processing tasks.”
NVIDIA's architecture runs every AI model and all data processing and parallel processing tasks.
-
Mixed
“A long time ago, NVIDIA used to be a GPU company.”
-
Resolved true
“NVIDIA Open Shell is open source.”
-
Resolved true
“Today we’re announcing the Nemotron 3 Ultra.”
NVIDIA announced Nemotron 3 Ultra, its next open model, at the keynote.
-
Resolved true
“It is the reason why we’re working with Cadence so hard to accelerate all of their tools on CUDA, because the agents are impatient.”
NVIDIA is working with Cadence to accelerate Cadence's tools on CUDA.
Verdicts are made automatically; how verdicts are made.