Active Parameters
176B
Context Length
66K
Modality
Text
Architecture
Mixture of Experts
KV Cache Rate
37 KB/tok
License
Apache 2.0
Release Date
10 Apr 2024
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.90 · Output: $0.90
Precision
Context
Workload Memory: 371.59 GB
FP16 · 8K context
Base Weights: 368.80 GB
KV Cache: 0.29 GB
Runtime & Graphs: 2.50 GB
8x NVIDIA H100 80GB
371.6 / 576.0 GB usable · TP 8
Determine requirements for your specific workload:
Open in VRAM Calculator
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 4.38.0
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
Rank
#220
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1230 | 181 |
Intelligence Index | 0.06 | 310 |
Summarization Archived | 0.587 | 25 |
Overall Rank
#220
Coding Rank
-
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.
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
48
Key-Value Heads
8
Position Embedding
ROPE
RoPE Theta
1,000,000
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Hidden Dimension Size
1,024
Number of Layers
56
FFN Intermediate Size (Dense)
16,384
Tokenizer
Vocabulary Size
32,000
Mixture of Experts
Total Expert Parameters
22.0B
Number of Experts
8
Active Experts
2
FFN Intermediate Size (per Expert)
16,384
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.