Cerebras Runs Gemma 4 31B at 35x GPU Speed on Its Cloud
Gemma 4 31B hits 1,851 tokens/sec on Cerebras wafer-scale hardware, making real-time multimodal and agentic loops practical for the first time
- Speed record: Gemma 4 31B runs at 1,851 tokens/sec on Cerebras, ~35x faster than typical GPU endpoints per Artificial Analysis benchmarks.
- First multimodal model on Cerebras: Gemma 4 is the first image-capable model on the platform, enabling real-time visual and agentic loops.
- Model quality: Scores 84.3% on GPQA Diamond and 80.0% on LiveCodeBench v6, comparable to Claude Haiku 4.5 but open-weight under Apache 2.0.
- How to access: Available now on Cerebras Inference Cloud with a free tier (1M tokens/day, no credit card) and pay-per-token pricing from $10.
- Why it matters: At 1,800+ TPS, multi-step agentic and vision loops become fast enough for real-time product experiences, not just faster batch jobs.
- Platform milestone: Cerebras says multimodal support will expand to additional models, making this the start of a new capability tier on wafer-scale hardware.
Multimodal inference just got a lot faster. Cerebras has launched Gemma 4 31B on its wafer-scale inference cloud, clocking in at a measured 1,851 output tokens per second according to third-party benchmarking firm Artificial Analysis. That is roughly 35 times the speed of a typical GPU endpoint running the same model, and it marks the first time a multimodal model has run at this kind of throughput on any public cloud.
This is not just a speed record for its own sake. The combination of vision support and extreme throughput is what changes what you can actually build.
Why agentic loops hate slow inference
The case for fast inference goes well beyond user experience. As agentic AI workflows proliferate, models are making many sequential calls, reasoning over longer context windows, and driving dramatically higher compute consumption. A single agentic task might call the model five or ten times in sequence: inspect an image, reason over it, call a tool, check the result, retry. As Cerebras CEO Andrew Feldman put it, "speed can become better answers. The longer your reasoning, the more iterations, the better answer you get."
At conventional GPU speeds of 50 to 100 tokens per second, those loops feel sluggish enough that developers design around them. At 1,800+ tokens per second, the loop becomes fast enough to keep a human or another agent in the feedback cycle in real time.
What Gemma 4 31B actually is
Gemma 4 31B is a dense 30.7B multimodal model supporting text, images, and video with a 256K context window, native thinking mode, function calling, and 140+ languages, released under Apache 2.0. Being a dense model (as opposed to a Mixture-of-Experts model, where only a fraction of parameters activate per token) means it achieves high quality without the large memory footprint that MoE architectures require.