Upstage's Solar 31B Hits 2,000 Tokens per Second on Cerebras Hardware
Upstage's Solar 31B now runs at up to 2,000 tokens/sec on Cerebras hardware, making deep research queries across hundreds of sources feel nearly instant.
- Speed milestone: Upstage's Solar 31B now runs on Cerebras hardware at up to 2,000 tokens/sec, demonstrated completing a deep research query across 246 sources.
- Why it matters: Agentic and deep research workloads chain hundreds of inference calls; at 2,000 tok/sec, multi-source research that takes minutes on GPUs finishes in seconds.
- Solar 31B credentials: Upstage's model ranked above GPT-4.1 on the Artificial Analysis Intelligence Index -- Korea's first frontier-class LLM -- while matching 70B-scale models at 31B parameters.
- Cerebras momentum: Fresh off the largest semiconductor IPO ever ($6.4B raised) and a $20B+ OpenAI deal, Cerebras is now expanding its inference platform to international AI labs.
- Upstage's rise: Korea's first generative AI unicorn, backed by $380M in sovereign investment, with 130%+ YoY revenue growth and enterprise deployments at Samsung and Korean insurers.
- Competitive signal: Cerebras runs 6.7x faster than the next-fastest GPU cloud on comparable workloads, putting direct pressure on GPU-based inference providers for agentic use cases.
Korea's Upstage AI and Cerebras Systems have announced a collaboration that puts Solar 31B -- Upstage's flagship language model -- on Cerebras inference hardware, hitting speeds of up to 2,000 tokens per second. To put that in perspective, Cerebras demonstrated the model completing a deep research query across 246 sources. That kind of multi-step, multi-source workload is exactly where raw inference speed changes the user experience from "go grab a coffee" to "watch it happen in real time."
Two companies with a lot to prove
Upstage was founded in 2020 by Sung Kim, a former professor at the Hong Kong University of Science and Technology who previously led Naver's Clova AI team. The company has been on a remarkable trajectory: it recently crossed the $1 billion valuation threshold to become the first generative AI company in Korea to achieve unicorn status, with total cumulative funding reaching approximately $279.7M. More significantly, Korea's financial authorities approved a 560 billion-won ($380.6 million) investment in Upstage -- a direct signal that Seoul sees the company as a national AI champion.
Cerebras, founded in 2016, built its reputation on a genuinely different approach to chip design. Its core product, the Wafer-Scale Engine, is substantially larger than standard GPUs -- rather than cutting a silicon wafer into hundreds of individual chips, Cerebras uses the entire wafer as one massive processor. That architecture is the reason for the speed: Cerebras solves the memory bandwidth bottleneck by building the largest chip in the world and storing the entire model on-chip, integrating 44GB of SRAM on a single chip and eliminating the need for external memory and the slow lanes linking external memory to compute.
Why 2,000 tokens/sec actually matters
For a single-turn chat, speed above ~100 tokens/sec is mostly invisible to a human reader. But deep research is a fundamentally different workload. The best research agents don't just summarize individual documents -- they follow citation trails, cross-reference findings across papers, identify contradictions in the literature, and produce structured reports that would take a human researcher days to compile. Each of those steps is a separate inference call, and the calls chain together.