Mistral AI · llama
Can I run mixtral?
A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.
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 contextmixtral 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-text-v0.1-q4_056B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 24.6 GB | ~27.5 GB |
| mixtral:8x7b-instruct-v0.1-q4_056B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 24.6 GB | ~27.5 GB |
| mixtral:8x7b-text-v0.1-q4_K_M56B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 26.5 GB | ~29.5 GB |
| mixtral:8x7b-instruct-v0.1-q4_K_M56B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 26.5 GB | ~29.5 GB |
| mixtral:8x7b-text-v0.1-q5_K_M56B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 30.9 GB | ~34.3 GB |
| mixtral:8x7b-instruct-v0.1-q5_K_M56B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 30.9 GB | ~34.3 GB |
| mixtral:8x7b-text-v0.1-q6_K56B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q6_K | 35.7 GB | ~39.5 GB |
| mixtral:8x7b-instruct-v0.1-q6_K56B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q6_K | 35.7 GB | ~39.5 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 mixtral locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull mixtral:8x7b-text-v0.1-q4_0 - 3.Check the source for the build's task. For text generation, run
ollama run mixtral:8x7b-text-v0.1-q4_0. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
Frequently asked questions about mixtral
- How much VRAM do I need to run mixtral?
- At 4K context, the smallest published build of mixtral (Q4_0) needs roughly 27.5 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 mixtral without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 27.5 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 mixtral download?
- The smallest published build is 24.6 GB. There are 24 builds in total, the largest being 262.0 GB. Leave some extra free disk space beyond the download itself.
- How do I run mixtral locally?
- Install Ollama, then download a specific build with "ollama pull mixtral:8x7b-text-v0.1-q4_0". 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 mixtral 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