Ollama Library · llama
Can I run cogito?
Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size, including counterparts from LLaMA, DeepSeek, and Qwen across most standard benchmarks.
Parameter counts and memory belong to each build below. A family can contain several sizes and tasks; fitting in memory is not a quality ranking.
Calculate memory for a build and contextcogito system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| cogito:3b3B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 2.1 GB | ~3.1 GB |
| cogito:3b-v1-preview-llama-q8_03B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 3.6 GB | ~4.7 GB |
| cogito:8b8B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 4.6 GB | ~5.8 GB |
| cogito:3b-v1-preview-llama-fp163B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 6.7 GB | ~8.1 GB |
| cogito:8b-v1-preview-llama-q8_08B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 8.0 GB | ~9.5 GB |
| cogito:14b14B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 8.4 GB | ~10.2 GB |
| cogito:14b-v1-preview-qwen-q8_014B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 14.6 GB | ~16.9 GB |
| cogito:32b32B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 18.5 GB | ~21.4 GB |
Showing the 8 smallest non-alias builds. Choose any build and change the context. A context above the build's documented maximum is a hypothetical calculation, not a supported setting.
How to run cogito locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull cogito:3b - 3.Check the source for the build's task. For text generation, run
ollama run cogito:3b. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
Frequently asked questions about cogito
- How much VRAM do I need to run cogito?
- At 4K context, the smallest published build of cogito (Q4_K_M) needs roughly 3.1 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run cogito without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 3.1 GB at 4K context, plus headroom for your operating system. Check the build's runtime requirements. We have not measured its speed on your CPU.
- How big is the cogito download?
- The smallest published build is 2.1 GB. There are 14 builds in total, the largest being 131.4 GB. Leave some extra free disk space beyond the download itself.
- How do I run cogito locally?
- Install Ollama, then download a specific build with "ollama pull cogito:3b". For a build that supports text generation, use ollama run with the same tag. Check the model source for its task and prompt format.
Will cogito run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Compare with similar models
Or start from your memory: 8 GB VRAM, 12 GB VRAM, 16 GB VRAM, 24 GB VRAM or a 16 GB Mac.
Model data from the official Ollama registry · verified 13/10/2026