mradermacher

/

model_requests

like 126

The mmproj files containing the vision stack for GLM-4.6V-Flash are now ready:

• F16: https://huggingface.co/mradermacher/GLM-4.6V-Flash-GGUF/blob/main/GLM-4.6V-Flash.mmproj-f16.gguf
• Q8_0 https://huggingface.co/mradermacher/GLM-4.6V-Flash-GGUF/blob/main/GLM-4.6V-Flash.mmproj-Q8_0.gguf

I assume providing them is enough and the quants itself don't need to be regenerated. Pleas test GLM-4.6V-Flash and let me know if it works. If it does, I will provide mmproj files for the other ones as well.

We apparently never made GLM-4.1V-9B-Thinking so it's queued.

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#GLM-4.1V-9B-Thinking-GGUF for quants to appear.