How to use from
Hermes Agent
Start the llama.cpp server
# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ngxson/glm4.5-small-test:Q4_K_M
Configure Hermes
# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:9931/v1
hermes config set model.default ngxson/glm4.5-small-test:Q4_K_M
Run Hermes
hermes
Quick Links

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

glm4.5-small-test

This model is made by removing all experts tensors, except for the first 2 experts

It generates gibberish output, only used for testing purpose

Downloads last month
26
GGUF
Model size
23B params
Architecture
glm4moe
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support