docs: fix outdated Ollama model names in documentation (#8551)

* docs: fix outdated Ollama model names in documentation

Fixes #7918

- Updated qwen3-coder-30b to qwen2.5-coder:32b (correct identifier)
- Replaced devstral-small with codellama:34b-code (existing model)
- Changed ollama run to ollama pull for initial download

* chore: add changeset for Ollama model names fix

.changeset/fix-ollama-model-names.md

@@ -0,0 +1,9 @@
+---
+"claude-dev": patch
+---
+
+docs: fix outdated Ollama model names in documentation
+
+Updated recommended Ollama models to use correct identifiers:
+- Changed qwen3-coder-30b to qwen2.5-coder:32b
+- Changed devstral-small to codellama:34b-code

docs/running-models-locally/ollama.mdx

@@ -73,16 +73,16 @@ Open VS Code and configure Cline:
 
 ### Recommended Models
 
-For the best experience with Cline, use **Qwen3 Coder 30B**. This model provides strong coding capabilities and reliable tool use for local development.
+For the best experience with Cline, use **Qwen 2.5 Coder 32B**. This model provides strong coding capabilities and reliable tool use for local development.
 
 To download it:
 ```bash
-ollama run qwen3-coder-30b
+ollama pull qwen2.5-coder:32b
 ```
 
 Other capable models include:
-- `mistral-small` - Good balance of performance and speed
-- `devstral-small` - Optimized for coding tasks
+- `mistral-small:latest` - Good balance of performance and speed
+- `codellama:34b-code` - Optimized for coding tasks
 
 ### Important Notes