Gemma 3 1B
by Google · gemma-3 family
1B
parameters
text-generation multilingual summarization
Gemma 3 1B is Google's ultra-lightweight model, ideal for edge devices and resource-constrained environments. Text-only (no vision at this size), it handles basic text generation and summarization tasks with minimal hardware requirements. At under 2 GB of VRAM for Q8, this model runs on virtually any modern hardware including older GPUs and base-config Macs.
Quick Start with Ollama
ollama run 1b-it-q8_0 | Creator | |
| Parameters | 1B |
| Architecture | transformer-decoder |
| Context | 32K tokens |
| Released | Mar 12, 2025 |
| License | Gemma Terms of Use |
| Ollama | gemma3:1b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M | 0.8 GB | 1.5 GB | | 1b-it-q4_K_M |
| Q8_0 rec | 1.1 GB | 2 GB | | 1b-it-q8_0 |
| F16 | 2 GB | 3.5 GB | | 1b-it-fp16 |
Compatible Hardware
Q8_0 requires 2 GB VRAM
Benchmark Scores
42.0
mmlu