4-bit 4bit Base model:google/gemma-3-12b-... Base model:quantized:google/ge... Conversational Gemma3 Mlx Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-3-12b-it-4bit-DWQ
Gemma 3 12B It 4bit DWQ Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Gemma 3 12B It 4bit DWQ Parameters and Internals
| LLM Name | Gemma 3 12B It 4bit DWQ |
| Repository 🤗 | https://huggingface.co/mlx-community/gemma-3-12b-it-4bit-DWQ |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 7.2 GB |
| Updated | 2025-09-13 |
| Maintainer | mlx-community |
| Model Type | gemma3 |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Gemma3ForConditionalGeneration |
| License | gemma |
| Transformers Version | 4.50.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Torch Data Type | bfloat16 |
Best Alternatives to Gemma 3 12B It 4bit DWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Fallen Gemma3 12B V1 | 128K / 24.3 GB | 1232 | 20 |
| Gemma 3 R1 12B V1 | 0K / 24.3 GB | 127 | 12 |
| Safeword Casual V1 12B | 0K / 24.3 GB | 26 | 3 |
| Amoral Fallen Omega Gemma3 12B | 0K / 24.2 GB | 9 | 17 |
| ...ga Abomination Gemma3 12B V1.0 | 0K / 24.2 GB | 58 | 9 |
| Oni Mitsubishi 12B | 0K / 23.4 GB | 15 | 35 |
| ...mega Directive Gemma3 12B V1.0 | 0K / 24.3 GB | 22 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-3-12b-it-4bit-DWQ .
Rank the Gemma 3 12B It 4bit DWQ Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51352 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124