← CanIRunLocal · All hardware · All models
Google · 0.27B parameters · embedding.
Ollama weight files: Default 0.38 GB (embeddinggemma-2:270m).
Yes on 56 machines in this list. The smallest is M1 8GB: Default, about 1 GB, roughly 143 tokens per second, via Ollama. ollama pull embeddinggemma-2:270m
ollama pull embeddinggemma-2:270mollama pull embeddinggemma-2:270mollama pull embeddinggemma-2:270mollama pull embeddinggemma-2:270m| Hardware | Runtime | Quant | Memory | Fit | Speed | Command |
|---|---|---|---|---|---|---|
| M1 8GB | Ollama | Default | 1 GB | fits in fast memory | ~143 tok/s | ollama pull embeddinggemma-2:270m |
| M2 8GB | Ollama | Default | 1 GB | fits in fast memory | ~211 tok/s | ollama pull embeddinggemma-2:270m |
| M3 8GB | Ollama | Default | 1 GB | fits in fast memory | ~211 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 3060 Ti 8GB | Ollama | Default | 1 GB | fits in fast memory | ~707 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 3070 8GB | Ollama | Default | 1 GB | fits in fast memory | ~707 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 4060 8GB | Ollama | Default | 1 GB | fits in fast memory | ~429 tok/s | ollama pull embeddinggemma-2:270m |
| RX 7600 8GB | Ollama | Default | 1 GB | fits in fast memory | ~455 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 3080 10GB | Ollama | Default | 1 GB | fits in fast memory | ~1200 tok/s | ollama pull embeddinggemma-2:270m |
| M1 16GB | Ollama | Default | 1 GB | fits in fast memory | ~143 tok/s | ollama pull embeddinggemma-2:270m |
| M2 16GB | Ollama | Default | 1 GB | fits in fast memory | ~211 tok/s | ollama pull embeddinggemma-2:270m |
| M3 16GB | Ollama | Default | 1 GB | fits in fast memory | ~211 tok/s | ollama pull embeddinggemma-2:270m |
| M4 16GB | Ollama | Default | 1 GB | fits in fast memory | ~253 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 3060 12GB | Ollama | Default | 1 GB | fits in fast memory | ~568 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 4070 12GB | Ollama | Default | 1 GB | fits in fast memory | ~796 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 5070 12GB | Ollama | Default | 1 GB | fits in fast memory | ~1061 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 4060 Ti 16GB | Ollama | Default | 1 GB | fits in fast memory | ~455 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 4070 Ti Super 16GB | Ollama | Default | 1 GB | fits in fast memory | ~1061 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 4080 16GB | Ollama | Default | 1 GB | fits in fast memory | ~1132 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 5080 16GB | Ollama | Default | 1 GB | fits in fast memory | ~1516 tok/s | ollama pull embeddinggemma-2:270m |
| RX 7800 XT 16GB | Ollama | Default | 1 GB | fits in fast memory | ~985 tok/s | ollama pull embeddinggemma-2:270m |
| RX 9070 XT 16GB | Ollama | Default | 1 GB | fits in fast memory | ~1011 tok/s | ollama pull embeddinggemma-2:270m |
| M2 24GB | Ollama | Default | 1 GB | fits in fast memory | ~211 tok/s | ollama pull embeddinggemma-2:270m |
| M3 24GB | Ollama | Default | 1 GB | fits in fast memory | ~211 tok/s | ollama pull embeddinggemma-2:270m |
| M4 24GB | Ollama | Default | 1 GB | fits in fast memory | ~253 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 3090 24GB | Ollama | Default | 1 GB | fits in fast memory | ~1478 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 4090 24GB | Ollama | Default | 1 GB | fits in fast memory | ~1592 tok/s | ollama pull embeddinggemma-2:270m |
| RX 7900 XTX 24GB | Ollama | Default | 1 GB | fits in fast memory | ~1516 tok/s | ollama pull embeddinggemma-2:270m |
| M1 Pro 32GB | Ollama | Default | 1 GB | fits in fast memory | ~421 tok/s | ollama pull embeddinggemma-2:270m |
| M2 Pro 32GB | Ollama | Default | 1 GB | fits in fast memory | ~421 tok/s | ollama pull embeddinggemma-2:270m |
| M4 32GB | Ollama | Default | 1 GB | fits in fast memory | ~253 tok/s | ollama pull embeddinggemma-2:270m |
| M3 Pro 36GB | Ollama | Default | 1 GB | fits in fast memory | ~316 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M4 Max (32c GPU) 36GB | Ollama | Default | 1 GB | fits in fast memory | ~863 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M5 Max (32c GPU) 36GB | Ollama | Default | 1 GB | fits in fast memory | ~968 tok/s | ollama pull embeddinggemma-2:270m |
| RTX 5090 32GB | Ollama | Default | 1 GB | fits in fast memory | ~2829 tok/s | ollama pull embeddinggemma-2:270m |
| M4 Pro 48GB | Ollama | Default | 1 GB | fits in fast memory | ~575 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M4 Max (40c GPU) 48GB | Ollama | Default | 1 GB | fits in fast memory | ~1149 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M5 Max (40c GPU) 48GB | Ollama | Default | 1 GB | fits in fast memory | ~1293 tok/s | ollama pull embeddinggemma-2:270m |
| M1 Max 64GB | Ollama | Default | 1 GB | fits in fast memory | ~842 tok/s | ollama pull embeddinggemma-2:270m |
| M2 Max 64GB | Ollama | Default | 1 GB | fits in fast memory | ~842 tok/s | ollama pull embeddinggemma-2:270m |
| M3 Max 64GB | Ollama | Default | 1 GB | fits in fast memory | ~842 tok/s | ollama pull embeddinggemma-2:270m |
| M4 Max 64GB | Ollama | Default | 1 GB | fits in fast memory | ~1149 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M4 Max (40c GPU) 64GB | Ollama | Default | 1 GB | fits in fast memory | ~1149 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M5 Max (40c GPU) 64GB | Ollama | Default | 1 GB | fits in fast memory | ~1293 tok/s | ollama pull embeddinggemma-2:270m |
| DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) | Ollama | Default | 1 GB | fits in fast memory | ~539 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M3 Ultra 96GB | Ollama | Default | 1 GB | fits in fast memory | ~1724 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M5 Ultra 96GB | Ollama | Default | 1 GB | fits in fast memory | ~2526 tok/s | ollama pull embeddinggemma-2:270m |
| M3 Max 128GB | Ollama | Default | 1 GB | fits in fast memory | ~842 tok/s | ollama pull embeddinggemma-2:270m |
| M4 Max 128GB | Ollama | Default | 1 GB | fits in fast memory | ~1149 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M4 Max (40c GPU) 128GB | Ollama | Default | 1 GB | fits in fast memory | ~1149 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M5 Max (40c GPU) 128GB | Ollama | Default | 1 GB | fits in fast memory | ~1293 tok/s | ollama pull embeddinggemma-2:270m |
| DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) | Ollama | Default | 1 GB | fits in fast memory | ~539 tok/s | ollama pull embeddinggemma-2:270m |
| M2 Ultra 192GB | Ollama | Default | 1 GB | fits in fast memory | ~1684 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M3 Ultra 256GB | Ollama | Default | 1 GB | fits in fast memory | ~1724 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M5 Ultra (64c GPU) 256GB | Ollama | Default | 1 GB | fits in fast memory | ~2526 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M5 Ultra (80c GPU) 256GB | Ollama | Default | 1 GB | fits in fast memory | ~2526 tok/s | ollama pull embeddinggemma-2:270m |
| Mac Studio M3 Ultra (80c GPU) 512GB | Ollama | Default | 1 GB | fits in fast memory | ~1724 tok/s | ollama pull embeddinggemma-2:270m |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-16.
A project by OnDevice Labs · llms.txt