French startup Kog says your company's existing GPUs can run AI ten times faster. Here's how.
Kog claims software alone can dramatically speed up AI inference on the chips businesses already own. That could matter a lot if it works at scale.
Key points
- French startup Kog drew 200 business leads in May 2025 after a public demo showing 3,000 tokens per second on standard data-centre GPUs.
- Its small test model, Laneformer 2B, has since been open-sourced, but Kog's real target is large language models used in everyday AI tools.
- CEO Gaël Delalleau says a first major model running at 10x speed should be ready to demonstrate by September 2025, ahead of a planned Series A fundraise.
- Kog's seed round was co-led by Varsity VC and backed by French public investors Bpifrance and the French Tech 2030 programme.
When you run AI software, every answer you get requires a process called inference: the model reads your question and generates a reply, word by word. The faster that happens, the less you wait and the less it costs. Right now, that speed is a genuine bottleneck for many businesses.
Kog, a Paris-based startup, thinks the bottleneck is not the hardware. It is the software running on top.
What is Kog actually claiming?
Kog says it can make AI inference dramatically faster without swapping out any chips. Its May demo, which first caught wide attention on the programmer forum Hacker News, showed a small AI model producing 3,000 tokens (roughly 3,000 words or word-fragments) per second on AMD MI300X and NVIDIA H200 GPUs, the kind of chips large companies already run in their data centres.
That figure came from a purpose-built model called Laneformer 2B, which has about 2 billion parameters (think of parameters as the learned settings inside an AI model that shape its answers). It is small by today's standards. The company has open-sourced it, but the hard commercial question is whether the same tricks work on the far larger models that power tools like Claude or ChatGPT.
Kog says yes. CEO Gaël Delalleau told TechCrunch he expects to demonstrate a major large model running at ten times its normal speed by September 2025. That milestone would unlock a Series A funding round, he said.
Who would actually benefit?
Practical gains would land first with software engineers and AI-heavy workflows. Users of Claude Code, Anthropic's coding assistant, sometimes wait hours for results. Anthropic already sells a "Fast Mode" at a premium price because speed has real value. Kog is pitching itself as a way to get that speed without paying the premium, using the infrastructure a company already has.
Design partners include platforms that let users generate games and apps from a text prompt. For those products, a faster result is not just a nice feature; it directly affects how many users pay.
Kog is not alone in this space. ZML, also French, released software that can bypass Nvidia's CUDA (the standard software layer that tells Nvidia chips how to work) to speed up inference across different hardware. Delalleau positions Kog differently, closer to Stanford's Hazy Research lab, with an even lower-level focus on GPU engineering.
| Fact | Detail |
|---|---|
| Demo speed | 3,000 tokens per second, single request |
| Test model | Laneformer 2B (2 billion parameters, open-sourced) |
| Target milestone | 10x speed on a major large model, September 2025 |
| Business leads from demo | 200, as of May 2025 |
| Team size | 11 people |
| Seed backers | Varsity VC, Bpifrance, French Tech 2030, Scaleway |
That low-level work is slow. For every new GPU model, Kog spends weeks to months studying how the chip actually behaves before writing a single line of optimisation code. With 11 people, that limits how many chips the company can support at once.
Common questions
Can this speed up the AI tools I already use at work?
Not yet for most people. Kog sells to companies running their own AI infrastructure, not to individual users. If a company uses Kog's software on its servers, you might notice faster results without knowing why.
What does "inference speed" actually mean for me?
Every time an AI tool answers a question, writes code or generates an image, that is one inference. Faster inference means shorter waits and lower running costs for the company providing the tool, which can translate to lower prices or better products over time.
Is Kog's big claim proven yet?
Not on large models. The 3,000-token-per-second result used a small, specially built model. Delivering comparable gains on the much bigger models that power mainstream AI tools is the company's next, harder test.
