4-bit 4bit Base model:google/medgemma-27b... Base model:quantized:google/me... Clinical-reasoning Conversational Gemma3 text Medical Mlx Quantized Region:us Safetensors Sharded Tensorflow Thinking
Model Card on HF 🤗: https://huggingface.co/mlx-community/medgemma-27b-text-it-4bit
Medgemma 27B Text It 4bit 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)
Medgemma 27B Text It 4bit Parameters and Internals
| LLM Name | Medgemma 27B Text It 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/medgemma-27b-text-it-4bit |
| Base Model(s) | |
| Model Size | 27b |
| Required VRAM | 16 GB |
| Updated | 2025-06-09 |
| Maintainer | mlx-community |
| Model Type | gemma3_text |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Gemma3ForCausalLM |
| License | other |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.52.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262144 |
| Torch Data Type | bfloat16 |
Best Alternatives to Medgemma 27B Text It 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Medgemma 27B Text It 8bit | 128K / 30.3 GB | 593 | 1 |
| Fallen Gemma3 27B V1 | 128K / 55.3 GB | 35876 | 37 |
| Gemma 3 27B It Abliterated V2 | 128K / 108.9 GB | 245 | 20 |
| Amoral Gemma3 27B V2 Qat | 128K / 55.3 GB | 728 | 15 |
| Gemma 3 27B Novision | 128K / 54.4 GB | 59 | 2 |
| ...emma 3 27B Experiment V2 Merge | 128K / 106.1 GB | 12 | 0 |
| ...a 3 27B Experiment Storyteller | 128K / 54.4 GB | 5 | 0 |
| Gemma 3 27B Fujin | 128K / 54.4 GB | 5 | 0 |
| G3 27B Part2 Confetti | 128K / 54.4 GB | 5 | 0 |
| G3 27B Part1 Glitter | 128K / 54.4 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/medgemma-27b-text-it-4bit .
Rank the Medgemma 27B Text It 4bit 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? 48023 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124