From The Register, August 24:
What Nvidia's first Groq 3 LPU benchmarks tell us about its $20B gamble
Gemma 4 31B performance tests offer a best-case scenario for next-gen dataflow accelerators
Nvidia’s $20 billion bet on Groq’s LPU tech sure looks like it was a good one. On Monday, the GPU giant offered the first glimpse of just how big a speedup its Groq 3-based LPX racks will provide.
In an independent benchmark conducted by Artificial Analysis, Nvidia’s LPX rack systems managed to churn out 3,400 tokens a second (tok/s) with a 100,000-token input sequence in Google’s Gemma 4 31B model.
According to Nvidia, this makes it 4x faster than the nearest alternative platform, which going off Artificial Analysis’ leaderboard would be a direct dig at Cerebras, which managed a still impressive 882 tok/s under the same conditions.
Acquihired by Nvidia in late December, Groq has LPUs that feature an SRAM-heavy dataflow architecture designed specifically for high-performance inference serving. Unlike traditional datacenter GPUs, which rely on high-speed DRAM memory tech like GDDR7 and HBM4, Groq’s chips rely entirely on a large pool of on-die SRAM orders of magnitude faster than even the best HBM stacks (around 2.75 TB/s each) available today. And when it comes to inference, memory bandwidth is the bottleneck to beat....
....MUCH MORE
Previously:
September 17, 2025 - Chips: Nvidia Challenger AI Inference Co., Groq, Raises $750 Million At Post-Money $6.9 Billion Valuation
We don't have much posted on Groq, only a half-dozen mentions in general articles on inference companies including SambaNova and Cerebras. One reason we do have it flagged is that the CIA's venture arm In-Q-Tel was an early investor. Another investor is Disruptive who seem to have an eye for pre-public companies:
...Palantir, Airbnb, Spotify, Shield AI, Hims, Databricks, Stripe, Slack...That's from Groq's September 17 press release, "Groq Raises $750 Million as Inference Demand Surges".
We have quite a bit more on the company in the link-vault, including this piece from The Technologist substack, February 13: Deep Dive 4: Groq (Private)
December 26, 2025 - "Nvidia Licenses Groq's AI Chip Tech, Grabs Top Execs In Not-Quite Takeover" (NVDA)
December 27, 2025 - "NVIDIA’s Christmas Eve 'Hackquisition' Miracle" (NVDA; GOOG)
December 28, 2025 - "Nvidia's Groq deal underscores how the AI chip giant uses its massive balance sheet to 'maintain dominance'" (NVDA)
March 21, 2026 - "Nvidia Finally Admits Why It Shelled Out $20 Billion For Groq" (and Senator Warren swings by) NVDA