gemma-4-12B-coder-fable5-composer2.5-v1-GGUF

$ ollama run gemma-4-12b-coder-fable5-composer2-5-v1-gguf

# pin the quantization explicitly
$ ollama run gemma-4-12b-coder-fable5-composer2-5-v1-gguf-q4_k_m

$ huggingface-cli download yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF-GGUF \
    gemma4-coding-Q4_K_M.gguf --local-dir .

$ llama-cli -m gemma4-coding-Q4_K_M.gguf \
    -c 8192 -ngl 99 -t 8 --color

$ curl -s https://aimodelscomparison.com/api/v1/models/gemma-4-12b-coder-fable5-composer2-5-v1-gguf
{
  "hf_id": "yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF",
  "params_b": null,
  "context_length": null,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 297697,
  "vram_estimates": [
    { "quant": "Q2_K", "gb": 5.8 },
    { "quant": "Q3_K_M", "gb": 7.2 }
  ],
  "updated_at": "2026-07-28T18:07:02Z"
}