Mistral Large 3 Architecture
Back to Mistral Large 3 in the gallery
Mistral AI
Mistral's new flagship effectively adopts the DeepSeek architecture and retunes the expert sizes.
Architecture and specifications
- Scale
- 673B total, 41B active (6.1% active)
- Context (tokens)
- 262,144
- License
- Apache License 2.0
- Date
- 2025-12-02
- Decoder type
- Sparse MoE
- Attention
- MLA
- Layer mix
- 61 MLA
- KV cache / token (bf16) info
- 68.6 KiB · Low
- Key detail
- Near-clone of DeepSeek V3 with larger experts, fewer routed experts, and multimodal support.
Training and benchmarks
- Pretraining data
- Not disclosed The model card describes training from scratch but does not report a training-token total. Mistral Large 3 model card
- Post-training methods
- Instruction tuning The released model is instruction-tuned; the card does not specify its supervised, preference, or RL training stages. Mistral Large 3 model card