gemma-4-E4B-it-heretic-mlx-bf16
Converted from coder3101/gemma-4-E4B-it-heretic with mlx_vlm.convert.
- Quantization: bf16
- q_bits: bf16
- q_mode: bfloat16
- Source type: Gemma 4 multimodal (Gemma4ForConditionalGeneration)
- Converter env: /Users/vanch/.cache/lm-studio/.venvs/gemma4-mlx
- Validation date: 2026-04-26
Validation Summary
- Status: passed local text and vision smoke tests
- Vision metadata present:
processor_config.jsonandpreprocessor_config.json - Peak memory across sampled tests: 16.793 GB
Validation Matrix
| Case | Output | Prompt TPS | Generation TPS | Peak Memory |
|---|---|---|---|---|
| Text: one-sentence model description | Gemma 4 is a family of open weights large language models developed by Google DeepMind. | 87.862 | 37.052 | 16.044 GB |
| Text: two-bullet structured answer | * The model belongs to the Gemma family of open-weights models. * It possesses multimodal capabilities, meaning it can process and understand different types of input, such as text and images. |
127.436 | 35.820 | 16.058 GB |
| Vision: red image color identification | The image is red. | 470.986 | 40.710 | 16.793 GB |
| Vision: blue image color identification | The image is blue. | 474.026 | 40.502 | 16.793 GB |
Local Artifacts
- Full verification logs:
/Users/vanch/models/gemma4-e4b-heretic-full-verify/bf16-*.log