---
title: NousResearch/Arete-27B
url: https://recentmodel.com/models/NousResearch/Arete-27B/
status: main board
published: 2026-11-06T19:31:28Z
updated: 2026-11-07T00:18:45Z
source: https://huggingface.co/NousResearch/Arete-27B
---

# NousResearch/Arete-27B

These are not identical decoding settings across all models. Dense, 27B params. Context: 256K tokens (config). License: apache-2.0. Vendor-reported: "We chose Inkling as the best open model with a positive eval on what we were targeting."

- Vendor-reported: We chose Inkling as the best open model with a positive eval on what we were targeting.

- **Org:** NousResearch
- **Released:** 2026-11-06
- **Status:** main board
- **License:** apache-2.0 (permissive)
- **Parameters:** 27.4B
- **Architecture:** dense · Qwen3_5ForConditionalGeneration
- **Context:** 262,144 tokens (config.json)
- **Task:** text-generation · text
- **Signal:** 605 HF likes · 7497 downloads · 5 X likes · 3 X post(s)

## Runs on

real quant files; sizing calculation, not tested.

- Q4 ~20.3 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~31.8 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~56.9 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/NousResearch/Arete-27B)
- [GGUF: bartowski/NousResearch_Arete-27B-GGUF](https://huggingface.co/bartowski/NousResearch_Arete-27B-GGUF)
- [MLX: mlx-community/Arete-27B-OptiQ-4bit](https://huggingface.co/mlx-community/Arete-27B-OptiQ-4bit)