Mistral AI · mixtral
Can I run Mixtral 8x7B?
Mistral AI's Mixtral 8x7B — sparse Mixture of Experts model. 46.7B total params, ~12.9B active per token.
46.7B parameters32K contexttextApache-2.01 builds
Mixtral 8x7B 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 |
|---|---|---|---|
| mixtral:8x7b | Q4_K_M | 26.0 GB | ~30.9 GB |
How to run Mixtral 8x7B locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run mixtral:8x7b - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about Mixtral 8x7B
- How much VRAM do I need to run Mixtral 8x7B?
- At 4K context, the smallest published build of Mixtral 8x7B (Q4_K_M) needs roughly 30.9 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 Mixtral 8x7B 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 30.9 GB of free RAM for the smallest build.
- How big is the Mixtral 8x7B download?
- The smallest published build is 26.0 GB. Leave some extra free disk space beyond the download itself.
- How do I run Mixtral 8x7B locally?
- Install Ollama, then run "ollama run mixtral:8x7b" in a terminal. The weights download on first use and an interactive session opens.
Will Mixtral 8x7B 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