Mistral Nemo 12B
Mistral
Mistral and NVIDIA collaboration, 128K context
Text Generation Local Mistral Family
Parameters
12B
params
Context Window
128K
tokens
Max Output
-
tokens
Input Price
-
per 1M tokens
Output Price
-
per 1M tokens
Mistral Family 8 models
The full Mistral line by generation — pricing and capabilities vary across the family.
Mistral
Medium 3 Latest
$0.4 / $2
in / out · 1M
Small 3.2
$0.1 / $0.3
in / out · 1M
Small 3 Latest
General purpose, instruction following, vision
32K
context
Large 3
$0.5 / $1.5
in / out · 1M
7B
General purpose, efficient inference
32K
context
Nemo 12B Current
Coding, reasoning, multilingual
128K
context
Capabilities
👁️
Vision
⚡
Function Calling
📋
JSON Mode
🌊
Streaming
💬
System Prompt
🖥️
Code Execution
🔍
Web Search
🔌
MCP Support
Local Model Specs
Quantization
Q4_K_M
Runtime
ollama
Details
- Release Date
- July 18, 2024
- Knowledge Cutoff
- April 1, 2024
- Source
- Local
- License
- Apache 2.0
- Model ID
- mistral-nemo-12b
Last updated: November 26, 2025