---
title: GrootTeam/Groot-65B-A6B-261023
url: https://recentmodel.com/models/GrootTeam/Groot-65B-A6B-261023/
status: just landed · new, unvetted
published: 2026-10-23T09:41:16Z
updated: 2026-10-23T11:26:00Z
source: https://huggingface.co/GrootTeam/Groot-65B-A6B-261023
---

# GrootTeam/Groot-65B-A6B-261023

Groot is a family of open-weight reasoning models for complex real-world tasks. Mixture-of-experts, 118B total, 6B active (256 experts, 10 per token). Context: 256K tokens (config). License: qwen-community-1.0. Vendor-reported: "Groot-65B-A6B-261023 beats Qwen3.5-122B-A10B on 14 of the 16 benchmarks, for example Terminal Bench 2.1 (63.37 vs 45.26), AutomationBench (41.50 vs 7.44) and SWE-bench Verified (56.11 vs 23.00)."

- Vendor-reported: Groot-65B-A6B-261023 beats Qwen3.5-122B-A10B on 14 of the 16 benchmarks, for example Terminal Bench 2.1 (63.37 vs 45.26), AutomationBench (41.50 vs 7.44) and SWE-bench Verified (56.11 vs 23.00).

- **Org:** GrootTeam
- **Released:** 2026-10-23
- **Status:** just landed · new, unvetted
- **License:** qwen-community-1.0 (restricted)
- **Parameters:** 118.3B total, 6.0B active
- **Architecture:** MoE · 256 experts, 10/token · Qwen4ExpForConditionalGeneration
- **Context:** 262,144 tokens
- **Task:** image-text-to-text · vision
- **Signal:** 3 HF likes · 46 downloads

## Runs on

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

- Q4 ~80.5 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), Strix Halo 128GB unified (~96GB usable), Mac 128GB, CPU only, 128GB RAM (slow)
- Q8 ~127.5 GB (estimated): 2× DGX Spark (256GB), Mac 192GB, Mac 256GB
- FP16 ~238.4 GB (estimated): Mac 512GB, CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/GrootTeam/Groot-65B-A6B-261023)