TeichAI

/

GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF

like 500

Follow

TeichAI 1.12k

Works for me in LM studio and llama.cpp. Could be a weird ollama issue. When I get a chance I will run some tests.

Here is what my curl call to Ollama looks like:

curl -X POST http://localhost:11434/api/chat   -d '{
    "model": "hf.co/TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF:Q3_K_M",
    "messages": [{"role": "user", "content": "What is 2+2?"}],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "add",
          "description": "Add two numbers",
          "parameters": {
            "type": "object",
            "properties": {
              "a": {"type": "number"},
              "b": {"type": "number"}
            },
            "required": ["a", "b"]
          }
        }
      }
    ],
    "stream": false
  }'   -H "Content-Type: application/json"
  
{"error":"hf.co/TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF:Q3_K_M does not support tools"}

hmm yea could be something with the ollama modelfile. I will look into a fix

Yea so the issue here is that we need to create the ollama model using the provided modelfile. You will want to:

1. Download the Modelfile from the repository files

2. Then from the directory the downloaded file is located you need to create the Ollama model using this modelfile:

   ollama create TeichAI-GLM-4.7-Flash-Claude-Opus-4.5-Distill -f ./Modelfile

3. Load the model using TeichAI-GLM-4.7-Flash-Claude-Opus-4.5-Distill instead of hf.co/TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF:Q3_K_M

If you want to use any other quants you will need to edit the top line of the Modelfile accordingly. Hopefully this helps and resolves your issue :)

I am suggesting this purely from this discussion I found as I dont use ollama. https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF/discussions/23

Please let me know if this works as I'm not sure if that fixed the issue

Worked perfectly! Thanks a lot 🙏🏽

Is it possible to update these instructions in the following location?

I dont know how to do it. Else I am happy to raise a pull request.

Glad to hear that worked!

Also I'm not really sure... I could update the model README with further Ollama instructions. I think hf controls those things

Yea so the issue here is that we need to create the ollama model using the provided modelfile. You will want to:

1. Download the Modelfile from the repository files

2. Then from the directory the downloaded file is located you need to create the Ollama model using this modelfile:

   ollama create TeichAI-GLM-4.7-Flash-Claude-Opus-4.5-Distill -f ./Modelfile

3. Load the model using TeichAI-GLM-4.7-Flash-Claude-Opus-4.5-Distill instead of hf.co/TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF:Q3_K_M

If you want to use any other quants you will need to edit the top line of the Modelfile accordingly. Hopefully this helps and resolves your issue :)

I am suggesting this purely from this discussion I found as I dont use ollama. https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF/discussions/23

Please let me know if this works as I'm not sure if that fixed the issue

Thanks! Works!