Mistral Nemo is a 12B model with a context window of 131.1K tokens and the Tekken tokenizer trained on 100+ languages, offering ~30% better source code compression and improved multilingual efficiency as a drop-in replacement for Mistral 7B.
import { streamText } from 'ai'
const result = streamText({ model: 'mistral/mistral-nemo', prompt: 'Why is the sky blue?'})Released July 1, 2024, Mistral Nemo was built in collaboration with NVIDIA and introduced the Tekken tokenizer, trained across 100+ languages, as its defining technical innovation. Tekken achieves ~30% better compression for source code compared to previous Mistral AI tokenizers, 2x better compression for Korean, and 3x better compression for Arabic. These compression gains directly reduce token consumption and cost.
At 12B parameters with a context window of 131.1K tokens, Mistral Nemo serves as a drop-in replacement for Mistral 7B. Mistral Nemo provides enhanced instruction following, multi-turn conversation quality, and code generation. Quantization-aware training enables FP8 inference without performance degradation. The combination of quantization awareness and Tekken compression gives Mistral Nemo deployment efficiency advantages.
Mistral Nemo's multilingual coverage spans English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. Mistral Nemo is available under Apache 2.0, with both base and instruct weights on HuggingFace.