Ministral 3 3B
Parameters
3B
Context Length
256K
Modality
Multimodal
Auxiliary Parameters
400M
Architecture
Dense
License
Apache 2.0
Release Date
2 Dec 2025
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.10 · Output: $0.10
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
256,000 tokens
Consumer
2x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#195
| Benchmark | Score | Rank |
|---|---|---|
Graduate-Level QA | 0.534 | 100 |
Agentic Index | 0.8 | 133 |
Coding Index | 0.05 | 153 |
Intelligence Index | 0.05 | 329 |
General Knowledge Reference | 0.707 | 26 |
Rankings
Overall Rank
#195
Coding Rank
#158
About Ministral 3 3B
Ministral 3 3B is a compact 3.8B multimodal model by Mistral AI engineered for fast, low-power vision and language processing on local devices. It features native function calling and tied embeddings across an extensive 256K token context window.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
32
Key-Value Heads
8
Attention Head Dimension
128
Position Embedding
Absolute Position Embedding
RoPE Theta
1,000,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
Layer Normalization
Activation Function
SwigLU
Dimensions
Auxiliary Parameters
400M
Hidden Dimension Size
3,072
Number of Layers
26
FFN Intermediate Size (Dense)
9,216
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
131,072
About Ministral 3
Ministral 3 is a family of efficient edge models with vision capabilities, available in 3B, 8B, and 14B parameter sizes. Designed for edge deployment with multimodal and multilingual support, offering best-in-class performance for resource-constrained environments.