gemma-4-12b-heretic-abliterated-GGUF

$ ollama run gemma-4-12b-heretic-abliterated-gguf

# pin the quantization explicitly
$ ollama run gemma-4-12b-heretic-abliterated-gguf-q4_k_m

$ huggingface-cli download culturerevolt/gemma-4-12b-heretic-abliterated-GGUF-GGUF \
    gemma-4-12b-heretic-Q4_K_M.gguf --local-dir .

$ llama-cli -m gemma-4-12b-heretic-Q4_K_M.gguf \
    -c 8192 -ngl 99 -t 8 --color

$ curl -s https://aimodelscomparison.com/api/v1/models/gemma-4-12b-heretic-abliterated-gguf
{
  "hf_id": "culturerevolt/gemma-4-12b-heretic-abliterated-GGUF",
  "params_b": null,
  "context_length": null,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 218522,
  "vram_estimates": [
    { "quant": "IQ3_XS", "gb": 6.3 },
    { "quant": "IQ4_XS", "gb": 7.8 }
  ],
  "updated_at": "2026-07-28T18:08:39Z"
}