Mixtral-8x7B-v0.1
Active Parameters
46.7B
Context Length
33K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Apache 2.0
Release Date
9 Dec 2023
Knowledge Cutoff
Nov 2022
API Pricing (per 1M)
Input: $0.45 · Output: $0.70
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
5x RTX 4090
24GB VRAM
Datacenter
2x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
32,768 tokens
Consumer
5x RTX 4090
24GB VRAM
Datacenter
2x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#181
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1197 | 160 |
Intelligence Index | 0.05 | 228 |
Rankings
Overall Rank
#181
Coding Rank
-
About Mixtral-8x7B-v0.1
Mixtral-8x7B-v0.1 is an open Sparse Mixture-of-Experts model from Mistral AI activating 12.9B parameters per token for high-efficiency inference. It delivers strong multilingual and coding performance across a 32K token context window.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
32
Key-Value Heads
8
Attention Head Dimension
128
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
Swish
Dimensions
Hidden Dimension Size
4,096
Number of Layers
32
FFN Intermediate Size (Dense)
14,336
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
32,000
Mixture of Experts
Total Expert Parameters
7.0B
Number of Experts
8
Active Experts
2
Shared Experts
-
FFN Intermediate Size (per Expert)
14,336
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.