4bit Autotrain compatible Base model:finetune:unsloth/ge... Base model:unsloth/gemma-3-1b-... Conversational En Endpoints compatible Gemma3 text Quantized Region:us Safetensors Unsloth
Model Card on HF 🤗: https://huggingface.co/Alamaks/Gema4b
Gema4b 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)
Gema4b Parameters and Internals
| LLM Name | Gema4b |
| Repository 🤗 | https://huggingface.co/Alamaks/Gema4b |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 2 GB |
| Updated | 2025-07-22 |
| Maintainer | Alamaks |
| Model Type | gemma3_text |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Gemma3ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.53.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262144 |
| Torch Data Type | bfloat16 |
Best Alternatives to Gema4b
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gemma 3 1B It Unsloth Bnb 4bit | 32K / 1 GB | 195593 | 3 |
| Gemma 3 1B It Qat 4bit | 32K / 0.7 GB | 46329 | 2 |
| Gemma 3 1B It Bnb 4bit | 32K / 1 GB | 4254 | 8 |
| ...a 3 1B It Qat Q4 0 Unquantized | 32K / 2 GB | 2000 | 8 |
| Gemma 3 1B Pt Unsloth Bnb 4bit | 32K / 1 GB | 2560 | 4 |
| Gemma 3 1B It Qat | 32K / 2 GB | 1016 | 1 |
| Gemma 3 1B Pt Bnb 4bit | 32K / 1 GB | 1658 | 3 |
| Gemma 3 1B It 8bit | 32K / 1.4 GB | 1252 | 3 |
| Gemma 3 1B It | 32K / 2 GB | 2352998 | 535 |
| Gemma 3 1B Pt | 32K / 2 GB | 90698 | 141 |
Note: green Score (e.g. "73.2") means that the model is better than Alamaks/Gema4b .
Rank the Gema4b 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? 49963 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124