Mistral AI · 1T (52B active) · Mixture of Experts
Mistral's largest open model — 1T multimodal MoE, 52B active, 160+ languages and 1M context Check if your GPU or Mac can run Mistral Large 4 locally — 558.8 GB min, 931.3 GB recommended.
2026-091024K context
Mixture of Experts
Total experts: 128
Active experts: 4
Active params: 52.0B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 320.6 GB | low | — |
| Q3_K_M | 3 | 448.7 GB | moderate | — |
| Q4_K_M | 4 | 512.7 GB | good | — |
| Q5_K_M | 5 | 640.8 GB | good | — |
| Q6_K | 6 | 768.8 GB | excellent | — |
| Q8_0 | 8 | 1025 GB | excellent | — |
| F16 | 16 | 2049.4 GB | lossless | — |
Can I run Mistral Large 4 locally?
- Can I run Mistral Large 4 locally?
- Mistral Large 4 needs about 558.8 GB of memory at a minimum and 931.3 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Mistral Large 4 need?
- At Q4_K_M, Mistral Large 4 uses about 512.7 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.