Nemo
MistralCompact
Tool UseStructured Output
About this model
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.
Performance Tier
Compact
Nemo is a compact model from Mistral : optimized for speed and affordability.
Small, fast, and affordable. Optimized for speed and low cost, great for high-volume or simple tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.020 |
| Output (completion) | $0.040 |
Capabilities
Context Length131K
Max Output Tokens16K
TokenizerMistral
Inputtext
Outputtext
Release DateJuly 19, 2024
Benchmarks
General Intelligence
MMLU
68%
Mathematics
MATH-500
55%
Programming
HumanEval
68.5%
Recommended Use Cases
General ChatSummarizationTranslation
Strengths
- Compact 12B model suitable for edge deployment
- Good multilingual capabilities
- Open-weight with Apache 2.0 license
- EU-based company — data sovereignty advantage
Limitations
- Limited performance due to small model size
- Outdated compared to newer Mistral models
Resources
This model may use your data for training
