Mixture-of-Experts: 46.7B total params but only 12.9B active per token. Near-70B quality at lower inference cost.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 26GB VRAM Recommended
The Mixtral 8x7B model by Mistral AI is a 46.7B (MoE) parameter architecture optimized for chat tasks. It requires approximately 24GB of VRAM to comfortably run locally using a Q4_K_M quantization. Extending the context window up to 32,768 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running Mixtral 8x7B at maximum tokens-per-second, we recommend using LM Studio or Ollama with a GGUF quantization (Q4_K_M or Q6_K). If you are multi-GPU, use vLLM to distribute the layers across your VRAM pool for optimal throughput.
You will need a GPU with at least 26GB of VRAM to run the Q4_K_M quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run mixtral' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.