Meta AI · llama4
Can I run llama4?
Meta's latest collection of multimodal models.
108.6B parameters10240K contextimagetext**LLAMA 4 COMMUNITY LICENSE AGREEMENT**6 builds
llama4 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 |
|---|---|---|---|
| llama4:17b-scout-16e-instruct-q4_K_M | Q4_K_M | 62.8 GB | ~90.2 GB(est.) |
| llama4:17b-scout-16e-instruct-q8_0 | Q8_0 | 108.5 GB | ~155.6 GB(est.) |
| llama4:17b-scout-16e-instruct-fp16 | F16 | 202.4 GB | ~289.8 GB(est.) |
| llama4:17b-maverick-128e-instruct-q4_K_M | Q4_K_M | 228.0 GB | ~326.5 GB(est.) |
| llama4:17b-maverick-128e-instruct-q8_0 | Q8_0 | 398.4 GB | ~570.1 GB(est.) |
| llama4:17b-maverick-128e-instruct-fp16 | F16 | 748.1 GB | ~1070.1 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 llama4 locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run llama4:17b-scout-16e-instruct-q4_K_M - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about llama4
- How much VRAM do I need to run llama4?
- At 4K context, the smallest published build of llama4 (Q4_K_M) needs roughly 90.2 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 llama4 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 90.2 GB of free RAM for the smallest build.
- How big is the llama4 download?
- The smallest published build is 62.8 GB. There are 6 builds in total, the largest being 748.1 GB. Leave some extra free disk space beyond the download itself.
- How do I run llama4 locally?
- Install Ollama, then run "ollama run llama4:17b-scout-16e-instruct-q4_K_M" in a terminal. The weights download on first use and an interactive session opens.
Will llama4 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