not compatible to ollama/qwen2.5-coder:7b #10402

Activity

1. yizhishang

   added

   bugSomething isn't workingSomething isn't working

   on Jan 24, 2026
2. github-actions

   assigned

   rekram1-node

   on Jan 24, 2026
3. github-actions

   added

   windows

   on Jan 24, 2026
4. github-actions commented on Jan 24, 2026

   

   github-actionsBot

   on Jan 24, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue might be a duplicate of existing issues. Please check:

   • Using local Ollama models doesnt return any results. #7083: Using local Ollama models doesnt return any results (mentions qwen2.5-coder:7b and qwen2.5-coder:32b with same configuration)
   • Model not returning the answers. #6223: Model not returning the answers (mentions qwen2.5-coder:14b with Ollama, tool calling issues)
   • Ollama: User message content arrives as empty array - model cannot see user input #5187: Ollama: User message content arrives as empty array - model cannot see user input (qwen2.5-coder:14b, Ollama configuration issue)
   • Weird error with toolcalling on local model #6649: Weird error with toolcalling on local model (local model via OpenAI-compatible endpoint, similar configuration)
   • Ollama custom provider error : agent configured model is not valid #8950: Ollama custom provider error: agent configured model is not valid (custom Ollama models configuration)

   Feel free to ignore if none of these address your specific case.
5. yizhishang commented on Jan 24, 2026

   

   yizhishang

   on Jan 24, 2026

   Author

   More actions

   {
     "$schema": "https://opencode.ai/config.json",
     "plugin": ["opencode-antigravity-auth@latest"],
     "provider": {
       "google": {
         "models": {
           "antigravity-gemini-3-pro": {
             "name": "Gemini 3 Pro (Antigravity)",
             "limit": { "context": 1048576, "output": 65535 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] },
             "variants": {
               "low": { "thinkingLevel": "low" },
               "high": { "thinkingLevel": "high" }
             }
           },
           "antigravity-gemini-3-flash": {
             "name": "Gemini 3 Flash (Antigravity)",
             "limit": { "context": 1048576, "output": 65536 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] },
             "variants": {
               "minimal": { "thinkingLevel": "minimal" },
               "low": { "thinkingLevel": "low" },
               "medium": { "thinkingLevel": "medium" },
               "high": { "thinkingLevel": "high" }
             }
           },
           "antigravity-claude-sonnet-4-5": {
             "name": "Claude Sonnet 4.5 (Antigravity)",
             "limit": { "context": 200000, "output": 64000 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
           },
           "antigravity-claude-sonnet-4-5-thinking": {
             "name": "Claude Sonnet 4.5 Thinking (Antigravity)",
             "limit": { "context": 200000, "output": 64000 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] },
             "variants": {
               "low": { "thinkingConfig": { "thinkingBudget": 8192 } },
               "max": { "thinkingConfig": { "thinkingBudget": 32768 } }
             }
           },
           "antigravity-claude-opus-4-5-thinking": {
             "name": "Claude Opus 4.5 Thinking (Antigravity)",
             "limit": { "context": 200000, "output": 64000 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] },
             "variants": {
               "low": { "thinkingConfig": { "thinkingBudget": 8192 } },
               "max": { "thinkingConfig": { "thinkingBudget": 32768 } }
             }
           },
           "gemini-2.5-flash": {
             "name": "Gemini 2.5 Flash (Gemini CLI)",
             "limit": { "context": 1048576, "output": 65536 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
           },
           "gemini-2.5-pro": {
             "name": "Gemini 2.5 Pro (Gemini CLI)",
             "limit": { "context": 1048576, "output": 65536 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
           },
           "gemini-3-flash-preview": {
             "name": "Gemini 3 Flash Preview (Gemini CLI)",
             "limit": { "context": 1048576, "output": 65536 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
           },
           "gemini-3-pro-preview": {
             "name": "Gemini 3 Pro Preview (Gemini CLI)",
             "limit": { "context": 1048576, "output": 65535 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
           }
         }
       },
   // add local ollama config
       "ollama": {
         "npm": "@ai-sdk/openai-compatible",
         "name": "Ollama (local)",
         "options": {
           "baseURL": "http://localhost:11434/v1"
         },
         "models": {
           "qwen2.5-coder:7b": {
             "name": "qwen2.5 coder 7b",
             "limit": { "context": 200000, "output": 64000 },
             "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
           }
         }
       }
     }
   }
6. KLee1248 commented on Feb 9, 2026

   

   KLee1248

   on Feb 9, 2026

   Last edited by KLee1248

   More actions

   I'm having the same issue, where the output seems to be the intended usage of the tool, but then the tool doesn't actually get used.

   I can replicate this with qwen2.5-coder, but it seems to be working for qwen3 (I'm trying to use qwen2.5 because it fits on my GPU and qwen3 does not).

   Example input (via OpenCode UI):

   Use the provided tools to create a new file named "todo.md" and put a string that says "hello" in it.
   

   Example output:

   {"name": "write", "arguments": {"content": "hello\n", "filePath": "/C:/Code/SimpleTester/todo.md"}}
   

   Opencode.json

   {
     "$schema": "https://opencode.ai/config.json",
     "provider": {
       "ollama": {
         "models": {
           "qwen2.5-coder-16k": {
             "_launch": true,
             "name": "qwen2.5-coder-16k"
           },
           "qwen3:4b": {
             "_launch": true,
             "name": "qwen3:4b"
           },
           "qwen3:8b": {
             "tools": true
           }
         },
         "name": "Ollama (local)",
         "npm": "@ai-sdk/openai-compatible",
         "options": {
           "baseURL": "http://127.0.0.1:11434/v1"
         }
       }
     }
   }
   

   ollama ps result:

   NAME                        ID              SIZE      PROCESSOR    CONTEXT    UNTIL
   qwen2.5-coder-16k:latest    209ec794ab47    6.3 GB    100% GPU     16384      4 minutes from now
   

   Note: Everything seems to work appropriately using qwen3:8b (albeit very slowly), so I'm guessing that it's something related to this specific model.

   Here is the result form "ollama show qwen2.5-coder-16k"

     Model
       architecture        qwen2
       parameters          7.6B
       context length      32768
       embedding length    3584
       quantization        Q4_K_M
   
     Capabilities
       completion
       tools
       insert
   
     Parameters
       num_ctx    16384
   
     System
       You are Qwen, created by Alibaba Cloud. You are a helpful assistant.
   
     License
       Apache License
       Version 2.0, January 2004
       ...
   

   OpenCode Desktop v1.1.53
   Ollama version: 0.15.6
   Windows 11 10.0.26200

   👍React with 👍2Reacted by Gabriela Moreira and Charles-Antoine Fournel
7. noelbautista91 commented on Feb 13, 2026

   

   noelbautista91

   on Feb 13, 2026

   More actions

   FWIW, only unsloth's qwen3 30B coder model worked for me, tool calling and all.
8. cfournel commented on Mar 14, 2026

   

   cfournel

   on Mar 14, 2026

   More actions

   any update on this ?
9. thdxr

   removed

   bugSomething isn't workingSomething isn't working

   windows

   on May 3, 2026
10. github-actions commented on Jul 6, 2026

    

    github-actionsBot

    on Jul 6, 2026 – with GitHub Actions

    Contributor

    More actions

    To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.
11. github-actions

    closed this as not plannedon Jul 6, 2026