Ollama Library · llama
Can I run vicuna?
General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
7B parameters4K contexttext42 builds
vicuna 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 |
|---|---|---|---|
| vicuna:7b-q4_0 | Q4_0 | 3.6 GB | ~5.5 GB(est.) |
| vicuna:7b | Q4_0 | 3.6 GB | ~5.5 GB(est.) |
| vicuna:7b-v1.5-16k-q4_0 | Q4_0 | 3.6 GB | ~5.5 GB(est.) |
| vicuna:7b-q4_K_M | Q4_K_M | 3.8 GB | ~5.8 GB(est.) |
| vicuna:7b-v1.5-q4_K_M | Q4_K_M | 3.8 GB | ~5.8 GB(est.) |
| vicuna:7b-v1.5-16k-q4_K_M | Q4_K_M | 3.8 GB | ~5.8 GB(est.) |
| vicuna:7b-q5_K_M | Q5_K_M | 4.5 GB | ~6.8 GB(est.) |
| vicuna:7b-v1.5-q5_K_M | Q5_K_M | 4.5 GB | ~6.8 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run vicuna locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run vicuna:7b-q4_0 - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about vicuna
- How much VRAM do I need to run vicuna?
- At 4K context, the smallest published build of vicuna (Q4_0) needs roughly 5.5 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 vicuna without a dedicated GPU?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 5.5 GB of free RAM for the smallest build.
- How big is the vicuna download?
- The smallest published build is 3.6 GB. There are 42 builds in total, the largest being 60.6 GB. Leave some extra free disk space beyond the download itself.
- How do I run vicuna locally?
- Install Ollama, then run "ollama run vicuna:7b-q4_0" in a terminal. The weights download on first use and an interactive session opens.
Will vicuna run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Model data from the official Ollama registry · verified 13/09/2026