Hermes · 8B · Desktop / import

Hermes 3 8B on a phone

Community favorite for creative writing and agent-style tool use.

Parameters
8B
Typical Q4
~4.7 GB (Q4)
RAM to budget
~7.2 GB
Engines
GGUF

Get it running

NousResearch Hermes-3-Llama-3.1-8B; function calling. Hugging Face: NousResearch/Hermes-3-Llama-3.1-8B.

Load in LM Studio or Ollama, then chat from the phone.

Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.

Phones that can run it

Tight (close other apps)