# Mixtral 8x7B: RAM and VRAM requirements

> Mixtral 8x7B is a 46.7B mistral model (Mixture-of-Experts, 12.9B active per token). At Q4_K_M it needs about **28.9 GB** to run and fits **7 of 39** tracked devices. Minimum to run: Nvidia GeForce RTX 5090 (32GB).

Last validated: 2026-06-15. Sources: Ollama, HuggingFace GGUF repos, vendor specs.

## Memory by quantization
| Quant | On disk | To run (4k context) |
| --- | --- | --- |
| Q4_K_M | 26.49 GB | ~28.9 GB |
| Q8_0 | 46.22 GB | ~48.6 GB |

Memory = weights + KV cache + ~0.8 GB runtime overhead, and varies ±15% with context length.

## Will it run on my device?
- **Apple M1 (8GB)** (8 GB): No, not enough memory
- **Generic Android Phone (8GB RAM)** (8 GB): No, not enough memory
- **iPhone 17 Pro** (12 GB): No, not enough memory
- **Nvidia GeForce RTX 4080 (16GB)** (16 GB): No, not enough memory
- **Google Pixel 10 Pro** (16 GB): No, not enough memory
- **Nvidia GeForce RTX 4090 (24GB)** (24 GB): No, not enough memory
- **Apple M4 Pro (48GB)** (48 GB): Yes, but tight
- **Apple M3 Ultra (256GB)** (256 GB): Yes, it runs — room for FP16

Full table of all 39 devices: https://localmodel.run/model/mixtral-8x7b

## How to run
Quickest path: `ollama run mixtral:8x7b`. On Mac, LM Studio (ships MLX) is fastest; on Linux, Ollama for chat or vLLM to serve; on Windows, LM Studio or Ollama.

## Details
- Parameters: 46.7B (MoE, 12.9B active per token)
- Default context: 32k tokens
- License: Apache-2.0 (commercial use: yes)
- Released: 2023-12
- HuggingFace: 673,704 downloads/mo, 4694 likes

## FAQ
### How much VRAM or RAM does Mixtral 8x7B need?
About 28.9 GB at Q4_K_M (weights 26.49 GB + KV cache + overhead) at a 4k context. Budget ~48.6 GB for Q8_0.
### Can Mixtral 8x7B run on a laptop?
Mixtral 8x7B is large; you need a high-memory Mac or a 24 GB+ GPU at Q4_K_M.
### Can I use Mixtral 8x7B commercially?
Yes, Apache-2.0 permits commercial use.

Sources: https://ollama.com/library/mixtral, https://ollama.com/library/mixtral/tags, https://huggingface.co/MaziyarPanahi/Mixtral-8x7B-Instruct-v0.1-GGUF, https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
More: https://localmodel.run/model/mixtral-8x7b