Autor: Jakub Rusinowski · Ostatnia aktualizacja: 8 września 2026
Nex-AGI's first agentic series, and the one that set the pattern: take someone else's open base weights, post-train them for tool use and autonomy, publish the result. The flagship is a DeepSeek-V3.1 post-train scoring 80.2 on tau2-Bench and 70.6 on SWE-bench Verified. Superseded by Nex-N2, but kept because the question 'what does a 671B agentic post-train need?' has a factual answer that does not change when the model stops being recommended.
| Licence | What it permits | Applies to |
|---|---|---|
MIT | Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution. | DeepSeek-V3.1-Nex-N1 671B |
| DeepSeek-V3.1-Nex-N1 671B | Min 406 GB VRAM · Q4_K_M · 128,000 ctx · |
The cheapest GPU that runs Nex-N1 locally (min 406 GB VRAM) is the Apple M3 Ultra (512 GB).
Install Ollama then run: ollama run
Minimum VRAM: 406 GB. For best results use Q4_K_M quantization.
Nex-N1 needs about 406 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: DeepSeek-V3.1-Nex-N1 671B (406 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Nex-N1's smallest variant needs about 406 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
Q4_K_M is the best balance of quality and VRAM for Nex-N1 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run . This downloads Nex-N1 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.