Models

All models available on ChatUI-energy

Active

Qwen/Qwen3_8B [Real energy consumption] Qwen's latest open model with improved role-playing, long text generation and structured data understanding.

Qwen/Qwen2.5-72B-Instruct [Energy consumption is an estimation based on mean power usage and inference time] The latest Qwen open model with improved role-playing, long text generation and structured data understanding.

meta-llama/Llama-3.3-70B-Instruct [Energy consumption is an estimation based on mean power usage and inference time] Ideal for everyday use. A fast and extremely capable model matching closed source models' capabilities. Now with the latest Llama 3.3 weights!

Qwen/QwQ-32B [Energy consumption is an estimation based on mean power usage and inference time] QwQ is the latest reasoning model released by the Qwen team, approaching the capabilities of R1 in benchmarks.

google/gemma-3-27b-it [Energy consumption is an estimation based on mean power usage and inference time] Google's latest open model with great multilingual performance, supports image inputs natively.

NousResearch/Hermes-3-Llama-3.1-8B [Energy consumption is an estimation based on mean power usage and inference time] Nous Research's latest Hermes 3 release in 8B size. Follows instruction closely.

mistralai/Mistral-Nemo-Instruct-2407 [Energy consumption is an estimation based on mean power usage and inference time] A small model with good capabilities in language understanding and commonsense reasoning.

microsoft/Phi-3.5-mini-instruct [Energy consumption is an estimation based on mean power usage and inference time] One of the best small models (3.8B parameters), super fast for simple tasks.