Mistral Large 2 is Mistral's flagship dense model — particularly strong on European languages (French, German, Spanish, Italian) and code (HumanEval ~92%). VRAM footprint is steep: ~270 GB FP16, ~75 GB Q4_K_M. Requires 2x H100, 4x A100 40 GB, or 4x RTX 6000 Ada. The Mistral Research License limits commercial deployment without a paid agreement.
Mistral Large 2 123B needs at minimum 74.4 GB of VRAM at Q4_K_M quantization (270.6 GB at FP16). The cheapest GPU that comfortably fits with KV-cache headroom is the Intel Data Center GPU Max 1550 (128 GB VRAM, $2,500 MSRP). Community benchmark submissions are open. This model exceeds 48 GB at Q4, so plan for a 2-or-more-GPU split.
Weights only. Add ~20-30% for KV cache at typical context lengths.
| Quant | VRAM | Quality | Notes |
|---|---|---|---|
| FP16 | 270.6 GB | Reference | Training-precision weights |
| Q8_0 | 135.3 GB | Near-lossless | 8-bit, ~0.1% perplexity hit |
| Q6_K | 109.6 GB | Very high | 6-bit, near Q8 quality |
| Q5_K_M | 93.4 GB | High | Strong middle ground |
| Q4_K_M | 74.4 GB | Balanced (recommended) | Default for local deployments |
| Q4_0 | 76.1 GB | Legacy 4-bit | Older GGUF, kept for compatibility |
| Q3_K_M | 58.2 GB | Lossy | When VRAM is very tight |
| Q2_K | 43.3 GB | Extreme | Rescue option, quality degrades visibly |
Filtered from MyAIHardware's GPU database. FP16 needs 270.6 GB; Q4_K_M needs 74.4 GB.
| GPU | Per-card VRAM | 2x | 4x | 8x |
|---|---|---|---|---|
| Apple Mac mini (M4 Pro, 64 GB) | 64 GB | 128 | 256 | 512 |
| Apple Mac Studio (M1 Max, 64 GB) | 64 GB | 128 | 256 | 512 |
| Apple Mac Studio (M1 Ultra, 64 GB) | 64 GB | 128 | 256 | 512 |
| Apple Mac Studio (M2 Max, 64 GB) | 64 GB | 128 | 256 | 512 |
| Apple Mac Studio (M2 Ultra, 64 GB) | 64 GB | 128 | 256 | 512 |
| Apple Mac Studio (M4 Max, 64 GB) | 64 GB | 128 | 256 | 512 |
We don't have community benchmarks for this exact model yet.
Official weights + popular runtime tags.
ollama pull mistral-largelms get bartowski/Mistral-Large-Instruct-2407-GGUFStep-by-step guides that use this model.
Models in a similar size or capability class.
Use these in papers, blog posts, or internal docs.
@misc{mistral-large-2-2024,
title={Mistral Large 2 123B},
author={Mistral AI},
year={2024},
url={https://huggingface.co/mistralai/Mistral-Large-Instruct-2407}
}Mistral AI (2024). Mistral Large 2 123B [Model card]. Hugging Face. https://huggingface.co/mistralai/Mistral-Large-Instruct-2407
Mistral Large 2 123B (Mistral, Mistral AI, 2024). Available at https://huggingface.co/mistralai/Mistral-Large-Instruct-2407.