# Ollama

> Markdown twin of https://roboterminal.app/companies/ollama · https://roboterminal.app/companies/ollama.md

## Key numbers

- **Claimed raise:** $65M
  - _"Ollama raised $65M from Theory Ventures."_
  - Source: @stretchcloud on X

## On shared sources

- [NVIDIA](https://roboterminal.app/companies/nvidia) (4)
- [Lm Studio](https://roboterminal.app/companies/lm-studio) (2)
- [Perplexity](https://roboterminal.app/companies/perplexity) (2)
- [vLLM](https://roboterminal.app/companies/vllm) (2)
- [Alibaba](https://roboterminal.app/companies/alibaba) (1)
- [Anthropic](https://roboterminal.app/companies/anthropic) (1)
- [Apple](https://roboterminal.app/companies/apple) (1)
- [China Telecom](https://roboterminal.app/companies/china-telecom) (1)
- [DeepSeek](https://roboterminal.app/companies/deepseek) (1)
- [Flint](https://roboterminal.app/companies/flint) (1)
- [Google](https://roboterminal.app/companies/google) (1)
- [Hugging Face](https://roboterminal.app/companies/hugging-face) (1)
- [Meta](https://roboterminal.app/companies/meta) (1)
- [OpenAI](https://roboterminal.app/companies/openai) (1)
- [Theory Ventures](https://roboterminal.app/companies/theory-ventures) (1)

## Pulse

- [@stretchcloud on X](https://x.com/stretchcloud/status/2113188357874630934)
  A coding model that runs at 125 tokens a second on a MacBook and beats most open models under 50 billion parameters on SWE-bench was built largely by another AI system that picked its own architecture…
- [@stretchcloud on X](https://x.com/stretchcloud/status/2112849877696958782)
  NVIDIA already has TensorRT-LLM. It also has Dynamo. This week it shipped a third local inference server anyway, and the part worth sitting with is why. Flare runs on Rust, not Python, and it's built …
- [@stretchcloud on X](https://x.com/stretchcloud/status/2099565090877886838)
  Local inference is becoming a product category, not just a benchmark table. Perplexity launched Portable Computer on Windows RTX PCs today. The orchestrator LLM, subagent LLM, and the full agent harne…
- [@stretchcloud on X](https://x.com/stretchcloud/status/2097542010143990196)
  Every time an agentic system routes a task from one model to another, the receiving model pays a prefill tax. It has to re-read the entire conversation from scratch, driving up both cost and latency. …
- [@stretchcloud on X](https://x.com/stretchcloud/status/2096158393006485929)
  Ollama raised $65M from Theory Ventures. 14 people. 8.9M developers. 85% of Fortune 500. That last number is the one I keep returning to. Large enterprises choosing to run models locally rather than c…
- [@stretchcloud on X](https://x.com/stretchcloud/status/2095294198886903921)
  The hybrid compute pattern is getting serious. Perplexity just open-sourced Lily, the local inference engine powering their Mac hybrid compute feature, and the architecture choices are worth understan…

---

Source: Roboterminal · https://roboterminal.app/companies/ollama.md