SemiAnalysis says Nvidia's first Rubin NVL72 benchmark submission serves the 2.8-trillion-parameter Kimi K3 at over 850 tokens per second per user, with more than three times the throughput on vLLM. Separately, startup Lithos AI reports over 2,100 tok...
VQV Signal
OPEN SOURCE
WATCH
TECHNICAL
Inference speed records: Nvidia's Rubin runs Kimi K3 at 850 tokens a second, and AMD chips push DeepSeek V4.1 Flash p...
SemiAnalysis says Nvidia's first Rubin NVL72 benchmark submission serves the 2.8-trillion-parameter Kimi K3 at over 850 tokens per second per user, with more than three times the throughput on vLLM. Separately, startup Lithos AI reports over 2,100 tok...
SemiAnalysis says Nvidia's first Rubin NVL72 benchmark submission serves the 2.8-trillion-parameter Kimi K3 at over 850 tokens per second per user, with more than three times the throughput on vLLM. Separately, startup Lithos AI reports over 2,100 tokens per second per user on DeepSeek V4.1 Flash using eight AMD...
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength 95%
Technical label WATCH
Public Interest 51
Category OPEN SOURCE
Reader Depth TECHNICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 90
Practical Impact Score 0
Novelty Interest Score 94
Consequence Score 34
Curiosity Score 0
Shareability Score 45
Topics
VQV surfaced this signal because it is recent, relevant to LLM Inference, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.