Mixtral-8x22B-v0.1
Active Parameters
176B
Context Length
66K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Apache 2.0
Release Date
10 Apr 2024
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.90 · Output: $0.90
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
19x RTX 4090
24GB VRAM
Datacenter
6x NVIDIA A100
80GB VRAM
Apple Silicon
4x Apple M3 Max
128GB VRAM
65,536 tokens
Consumer
20x RTX 4090
24GB VRAM
Datacenter
6x NVIDIA A100
80GB VRAM
Apple Silicon
4x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#191
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1229 | 166 |
Intelligence Index | 0.06 | 240 |
Summarization Archived | 0.587 | 25 |
Rankings
Overall Rank
#191
Coding Rank
-
About Mixtral-8x22B-v0.1
Mixtral-8x22B-v0.1 is Mistral AI's 176B Sparse Mixture-of-Experts model activating 39B parameters for complex mathematical, coding, and multilingual tasks. It features native function calling and high computational throughput across a 64K context window.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
48
Key-Value Heads
8
Attention Head Dimension
-
Position Embedding
ROPE
RoPE Theta
1,000,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Auxiliary Parameters
-
Hidden Dimension Size
1,024
Number of Layers
56
FFN Intermediate Size (Dense)
16,384
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
32,000
Mixture of Experts
Total Expert Parameters
22.0B
Number of Experts
8
Active Experts
2
Shared Experts
-
FFN Intermediate Size (per Expert)
16,384
Dense Layers Before MoE
-
About Mixtral
The Mixtral model family, developed by Mistral AI, employs a sparse Mixture-of-Experts (SMoE) architecture. This design utilizes multiple expert networks per layer, where a router selects a subset to process each token. This enables large total parameter counts while maintaining computational efficiency by activating only a fraction of parameters per forward pass.