---
title: togethercomputer/HybridAgent-8B-Agentic
url: https://recentmodel.com/models/togethercomputer/HybridAgent-8B-Agentic/
status: archived · low-signal
published: 2026-10-09T23:53:37Z
updated: 2026-10-22T23:27:46Z
source: https://huggingface.co/togethercomputer/HybridAgent-8B-Agentic
---

# togethercomputer/HybridAgent-8B-Agentic

HybridAgent is an LLM agent that dynamically navigates between latent reasoning and text-based interaction within a single generation process. Dense, 8.2B params. Context: 32K tokens (config). License: mit.


- **Org:** togethercomputer
- **Released:** 2026-10-09
- **Status:** archived · low-signal
- **License:** mit (permissive)
- **Parameters:** 8.2B
- **Architecture:** dense · Qwen3ForCausalLM
- **Context:** 32,768 tokens
- **Task:** text-generation · text
- **Signal:** 8 HF likes · 1195 downloads
- **Archived:** 2026-10-22 (no longer listed by the collector; stats as last seen)

## Runs on

real quant files; sizing calculation, not tested.

- Q4 ~7.2 GB: no listed device
- Q8 ~10.9 GB: 12GB GPU (RTX 3060), 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 16GB GPU (7800 XT / 9070 XT), Mac 16GB, Mac 24GB
- FP16 ~18.6 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), 24GB GPU (7900 XTX), Strix Halo 128GB unified (~96GB usable), Arc B60 24GB, Arc B70 32GB, Mac 36GB, Mac 48GB, Mac 64GB (M1 Max), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 32GB RAM (slow), CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/togethercomputer/HybridAgent-8B-Agentic)