Mistral Large 4 — local AI model by Mistral AI
Written by Jakub Rusinowski · Last updated
Mistral's open-weight flagship, released as weights on 29 October 2026 after a three-week API-only preview: a mixture-of-experts model with about 1 trillion parameters in total and 52B active per token, a 1M-token context and image input. Every expert must be resident, so it is a datacentre model to self-host; the one single-machine route is a 2-bit GGUF on 512 GB of unified memory.
Variants
The smallest Mistral Large 4 variant needs about 636 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Mistral Large 4 1T-A52B → 1T (52B active) | ~635.6 GB | 1,048,576 | cloud-hosted tag |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Mistral Large 4 locally
Install Ollama, then pull the tag.
Ollama lists Mistral Large 4 only as the cloud tag mistral-large-4:cloud, which runs on Ollama's servers, not your machine. Locally, use llama.cpp (mainline since 29 October 2026) with the ggml-org GGUFs, or vLLM / SGLang on a multi-GPU server.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Applies to: Mistral Large 4 1T-A52BMistral Large 4 — frequently asked questions
How much VRAM does Mistral Large 4 need?
Mistral Large 4 needs about 636 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Mistral Large 4 1T-A52B (636 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Mistral Large 4 on an RTX 4090 (24 GB)?
Mistral Large 4's smallest variant needs about 636 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for Mistral Large 4?
Q4_K_M is the best balance of quality and VRAM for Mistral Large 4 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Mistral Large 4 with Ollama?
Mistral Large 4 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.