Translategemma 4B It 4bit is an open-source language model by mlx-community. Features: 4b LLM, VRAM: 2.2GB, License: gemma, Quantized.
4-bit 4bit Base model:google/translategem... Base model:quantized:google/tr... Conversational Gemma3 Mlx Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/translategemma-4b-it-4bit
Translategemma 4B It 4bit Parameters and Internals
| LLM Name | Translategemma 4B It 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/translategemma-4b-it-4bit |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 2.2 GB |
| Updated | 2026-03-30 |
| Maintainer | mlx-community |
| Model Type | gemma3 |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Gemma3ForConditionalGeneration |
| License | gemma |
| Transformers Version | 4.57.3 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
Best Alternatives to Translategemma 4B It 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Translategemma 4B It 8bit | 0K / 4.1 GB | 700 | 6 |
| Medgemma 4B It Abliterated | 128K / 6.3 GB | 14 | 6 |
| Gemma 3 Glitter 4B | 128K / 8.6 GB | 334 | 7 |
| Fallen Gemma3 4B V1 | 128K / 8.6 GB | 9 | 18 |
| ...on Content Safety Reasoning 4B | 0K / 10 GB | 3354 | 19 |
| Gemma 3 R1 4B V1 | 0K / 8.6 GB | 4 | 16 |
| X Ray Alpha | 0K / 8.6 GB | 334 | 122 |
| Medra4b Abliterated | 0K / 10 GB | 8 | 4 |
| ...4B It French Medical Assistant | 0K / 8.6 GB | 38 | 1 |
| Medra4b | 0K / 8.6 GB | 3 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/translategemma-4b-it-4bit .
Rank the Translategemma 4B 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? 52286 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a