Skip to content

Mistral Nemo

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.

Tool Use
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'mistral/mistral-nemo',
  prompt: 'Why is the sky blue?'
})
OverviewPlaygroundAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ

Frequently Asked Questions

  • What is the Tekken tokenizer?

    Tekken is a tokenizer trained on 100+ languages, introduced with Mistral Nemo. Tekken achieves ~30% better source code compression, 2x better compression for Korean, and 3x better compression for Arabic compared to previous Mistral AI tokenizers.

  • What is the context window for Mistral Nemo?

    131.1K tokens.

  • Is Mistral Nemo a drop-in replacement for Mistral 7B?

    Yes. Mistral AI positions it as a drop-in upgrade with the same architecture family, improved quality, and a larger context window.

  • What languages does Mistral Nemo support?

    English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi, among others.

  • What is FP8 inference and how does quantization-aware training help?

    FP8 is a reduced-precision number format that speeds inference and reduces memory usage. Quantization-aware training means the model was trained to tolerate FP8 quantization, so accuracy doesn't degrade compared to full-precision inference.

  • What is the license for Mistral Nemo?

    Apache 2.0, permitting commercial use and modification.

  • Who built Mistral Nemo?

    Mistral AI in collaboration with NVIDIA, as indicated by the NeMo branding aligned with NVIDIA's NeMo framework ecosystem.