---
title: open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.21
url: https://recentmodel.com/models/open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.21/
status: archived
published: 2026-09-22T07:41:15Z
updated: 2026-10-21T23:23:07Z
source: https://huggingface.co/open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.21
---

# open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.21

Text generation model from open-athena (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 67B total, 2B active (256 experts, 4 per token). Context: 256K tokens (config). License: openmdw-1.1.


- **Org:** open-athena
- **Released:** 2026-09-22
- **Status:** archived
- **License:** openmdw-1.1 (permissive)
- **Parameters:** 67.1B total, 2.0B active
- **Architecture:** MoE · 256 experts, 4/token · GrugMoeForCausalLM
- **Context:** 262,144 tokens
- **Task:** text-generation · text
- **Signal:** 0 HF likes · 5394 downloads
- **Archived:** 2026-10-21 (no longer listed by the collector; stats as last seen)

## Runs on

mixed: real files + estimate; sizing calculation, not tested.

- Q4 ~41.7 GB (estimated): 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), Mac 96GB, CPU only, 64GB RAM (slow)
- Q8 ~72.8 GB (estimated): 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), Strix Halo 128GB unified (~96GB usable), Mac 128GB, CPU only, 128GB RAM (slow)
- FP16 ~135.7 GB: 2× DGX Spark (256GB), Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.21)