Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_KEEP_ALIVE | No | Keep models loaded for 24 hours | 24h |
| OLLAMA_NUM_PARALLEL | No | Handle parallel requests | 8 |
| OLLAMA_KV_CACHE_TYPE | No | High-quality 8-bit cache | q8_0 |
| OLLAMA_FLASH_ATTENTION | No | Enable efficient attention mechanism | 1 |
| OLLAMA_MAX_LOADED_MODELS | No | Keep models in memory simultaneously | 4 |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| qwen3_code_review | Review code using Qwen3-Coder |
| qwen3_code_explain | Explain code using Qwen3-Coder |
| qwen3_code_generate | Generate code using Qwen3-Coder |
| qwen3_code_fix | Fix bugs in code using Qwen3-Coder |
| qwen3_code_optimize | Optimize code using Qwen3-Coder |