Nex-N2-Pro
Q4 GGUF download: bartowski/nex-agi_Nex-N2-Pro-GGUF - 38.96 GB on disk, read 2026-09-27. VRAM figures above are estimates; this is the actual file size.
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
28.2
AA Index
Coding
59.1
AA Index
Agentic
23.7
AA Index
Intelligence Index - Nex-N2-Pro vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Coding Index comparison
Agentic Index comparison
Benchmark data from Artificial Analysis · updated 2026-10-01.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| GPQA Diamond | 89.2 |
| HLE | 33.7 |
| SciCode | 43.3 |
| IFBench | 66.2 |
Source: Artificial Analysis component evals - updated 2026-10-01.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve nex-agi/Nex-N2-ProNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Nex-N2-Pro is a 396.8B-parameter apache-2.0 model from Nex AGI. It scores 28.2 on the Artificial Analysis Intelligence Index (coding 59.1). At Q4_K_M it needs roughly 230 GB of VRAM, placing it in the 48 GB+ / multi-GPU hardware tier.
Benchmarks
Artificial Analysis Intelligence Index - Nex-N2-Pro vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| Nex-N2-Pro | 41 | 59.1 | 89.2 |
| Claude Fable 5 (with fallback) | 59.9 | 76.5 | 92.6 |
| GPT-5.6 Sol (max) | 58.9 | 77.4 | 94.1 |
| Claude Opus 4.8 (max) | 55.7 | 74.3 | 92 |
| GPT-5.6 Terra (max) | 55 | 76.7 | 92.5 |
| GPT-5.5 (xhigh) | 54.8 | 74.9 | 93.5 |
Source: Artificial Analysis (2026-07-11).
Popularity
Nex-N2-Pro has 6,023 downloads in the last month on HuggingFace and 367 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Nex-N2-Pro need?
Nex-N2-Pro with 396.8B parameters needs approximately 230 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Nex-N2-Pro better than other nex-agi models?
Nex-N2-Pro has 396.8B parameters with 262,144 context - a strong choice for general use.
What license is Nex-N2-Pro under?
Nex-N2-Pro is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs Nex-N2-Pro well?
With 396.8B parameters, Nex-N2-Pro requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Nex-N2-Pro?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~282 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Nex-N2-Pro's context window handle?
Nex-N2-Pro supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Nex-N2-Pro?
Nex-N2-Pro competes with other 198B–595B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec