[monkmartinez]

ollama pull hf.co/unsloth/Qwen3-30B-A3B-GGUF:Q4_K_M and the modelfile comes with it. It may have errors in the template or parameters this way. It has to be converted to GGUF/GGML prior to using it this way. You can, of course, convert and create the specific ollama model from bf16 safetensors as well.

[rahimnathwani]

Yeah when I do this, the modelfile has only FROM and TEMPLATE. No PARAMETERs:

  ollama pull hf.co/jedisct1/MiMo-7B-RL-GGUF:Q4_K_M
  ollama show --modelfile hf.co/jedisct1/MiMo-7B-RL-GGUF:Q4_K_M