Meta AI · llama
Can I run llama-pro?
An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.
8B parameters4K contexttext12 builds
llama-pro 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 |
|---|---|---|---|
| llama-pro:8b-text-q4_0 | Q4_0 | 4.4 GB | ~6.7 GB(est.) |
| llama-pro:8b-instruct-q4_0 | Q4_0 | 4.4 GB | ~6.7 GB(est.) |
| llama-pro:8b-text-q4_K_M | Q4_K_M | 4.7 GB | ~7.1 GB(est.) |
| llama-pro:8b-instruct-q4_K_M | Q4_K_M | 4.7 GB | ~7.1 GB(est.) |
| llama-pro:8b-text-q5_K_M | Q5_K_M | 5.5 GB | ~8.3 GB(est.) |
| llama-pro:8b-instruct-q5_K_M | Q5_K_M | 5.5 GB | ~8.3 GB(est.) |
| llama-pro:8b-text-q6_K | Q6_K | 6.4 GB | ~9.5 GB(est.) |
| llama-pro:8b-instruct-q6_K | Q6_K | 6.4 GB | ~9.5 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 llama-pro locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run llama-pro:8b-text-q4_0 - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about llama-pro
- How much VRAM do I need to run llama-pro?
- At 4K context, the smallest published build of llama-pro (Q4_0) needs roughly 6.7 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 llama-pro 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 6.7 GB of free RAM for the smallest build.
- How big is the llama-pro download?
- The smallest published build is 4.4 GB. There are 12 builds in total, the largest being 15.6 GB. Leave some extra free disk space beyond the download itself.
- How do I run llama-pro locally?
- Install Ollama, then run "ollama run llama-pro:8b-text-q4_0" in a terminal. The weights download on first use and an interactive session opens.
Will llama-pro 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