Mistral-Small-2501
Parameters
24B
Context Length
33K
Modality
Text
Architecture
Dense
KV Cache Rate
120 KB/tok
License
Apache 2.0
Release Date
13 Jan 2025
Knowledge Cutoff
Oct 2023
API Pricing (per 1M)
Input: $0.05 · Output: $0.08
Hardware Sizing
Precision
Context
Workload Memory: 14.61 GB
INT4 · 8K context
Base Weights: 11.18 GB
KV Cache: 0.94 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
14.6 / 21.6 GB usable
2x RTX 4090 24GB
14.6 / 43.2 GB usable · TP 2
Apple M4 24GB
14.6 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
Rank
#185
| Benchmark | Score | Rank |
|---|---|---|
StackUnseen | 0.12 | 35 |
Professional Knowledge | 0.663 | 51 |
Graduate-Level QA | 0.461 | 109 |
General Text | 1274 | 174 |
Intelligence Index | 0.07 | 286 |
StackEval Archived | 0.811 | 13 |
Summarization Archived | 0.747 | 17 |
Rankings
Overall Rank
#185
Coding Rank
#165
About Mistral-Small-2501
Mistral Small 3 (2501) is a 24B-parameter dense model from Mistral AI engineered for rapid response times and high-throughput enterprise tasks. Released under Apache 2.0, it offers low-latency reasoning and function calling across a 32K context window.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
24
Key-Value Heads
6
Attention Head Dimension
128
Position Embedding
ROPE
RoPE Theta
100,000,000
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
32,768
Number of Layers
40
FFN Intermediate Size (Dense)
32,768
Tokenizer
Vocabulary Size
131,072
About Mistral Small 3
Mistral Small 3, a 24 billion parameter model, was designed for efficient, low-latency generative AI tasks. Its optimized architecture supports local deployment and includes multimodal understanding, multilingual capabilities, and a 128,000-token context window.
Other Mistral Small 3 Models
- No related models available