Available Models

All models you can pull and run with Koda.

All models use Q4_K_M quantization — a good balance of quality and size.

Run koda list --available to see the current list.

Model Library

Name	Description	Size
`llama3.2` / `llama3.2:3b`	Meta Llama 3.2 3B Instruct	2.0 GB
`llama3.1` / `llama3.1:8b`	Meta Llama 3.1 8B Instruct	4.9 GB
`mistral`	Mistral 7B Instruct v0.3	4.4 GB
`phi3`	Microsoft Phi-3 Mini 4K	2.2 GB
`gemma2`	Google Gemma 2 2B Instruct	1.6 GB
`qwen2.5`	Qwen 2.5 7B Instruct	4.7 GB
`deepseek-r1`	DeepSeek R1 Distill Qwen 7B	4.7 GB

Pulling a Model

koda pull llama3.2
koda pull mistral
koda pull gemma2

Running a Model

koda run llama3.2

CLI Reference

All Koda CLI commands with usage examples.

API Server

Koda's API server implements both Ollama and OpenAI protocols.

On this page

Model Library Pulling a Model Running a Model