Mistral Nemo
Mistral·
LLMssmallcloud + localEdge / Consumer
Overview
12B parameter model developed in collaboration with NVIDIA.
Capabilities and innovations
12B ParametersApache 2.0128k contextNVIDIA CollaborationTekken TokenizerEfficient 12B Scale
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| MMLU | 68% | unsourced |
- GPQA Diamond: not reported by the vendor
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Verified: not reported by the vendor
- SWE-bench Pro: benchmark did not exist at release
- MMLU-Pro: benchmark did not exist at release
- Terminal-Bench 2.x: benchmark did not exist at release
- MMMU-Pro: benchmark did not exist at release
Architecture and hardware
- Parameters
- 12B total (Dense)
- Estimated VRAM at Q4
- ~7 GB, Edge / Consumer class
Links
More from Mistral
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.