← CanIRunLocal · All hardware · All models
Prism ML · 9B parameters · chat, vision, reasoning.
Ollama weight files: Q2_0 3.2 GB (bonsai-2:9b).
Yes on 56 machines in this list. The smallest is M1 8GB: Q2_0, about 4.6 GB, roughly 17 tokens per second, via Ollama. ollama run bonsai-2:9b
ollama run bonsai-2:9bollama run bonsai-2:9bollama run bonsai-2:9bollama run bonsai-2:9b| Hardware | Runtime | Quant | Memory | Fit | Speed | Command |
|---|---|---|---|---|---|---|
| M1 8GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~17 tok/s | ollama run bonsai-2:9b |
| M2 8GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~25 tok/s | ollama run bonsai-2:9b |
| M3 8GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~25 tok/s | ollama run bonsai-2:9b |
| RTX 3060 Ti 8GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~84 tok/s | ollama run bonsai-2:9b |
| RTX 3070 8GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~84 tok/s | ollama run bonsai-2:9b |
| RTX 4060 8GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~51 tok/s | ollama run bonsai-2:9b |
| RX 7600 8GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~54 tok/s | ollama run bonsai-2:9b |
| RTX 3080 10GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~143 tok/s | ollama run bonsai-2:9b |
| M1 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~17 tok/s | ollama run bonsai-2:9b |
| M2 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~25 tok/s | ollama run bonsai-2:9b |
| M3 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~25 tok/s | ollama run bonsai-2:9b |
| M4 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~30 tok/s | ollama run bonsai-2:9b |
| RTX 3060 12GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~68 tok/s | ollama run bonsai-2:9b |
| RTX 4070 12GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~94 tok/s | ollama run bonsai-2:9b |
| RTX 5070 12GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~126 tok/s | ollama run bonsai-2:9b |
| RTX 4060 Ti 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~54 tok/s | ollama run bonsai-2:9b |
| RTX 4070 Ti Super 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~126 tok/s | ollama run bonsai-2:9b |
| RTX 4080 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~134 tok/s | ollama run bonsai-2:9b |
| RTX 5080 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~180 tok/s | ollama run bonsai-2:9b |
| RX 7800 XT 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~117 tok/s | ollama run bonsai-2:9b |
| RX 9070 XT 16GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~120 tok/s | ollama run bonsai-2:9b |
| M2 24GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~25 tok/s | ollama run bonsai-2:9b |
| M3 24GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~25 tok/s | ollama run bonsai-2:9b |
| M4 24GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~30 tok/s | ollama run bonsai-2:9b |
| RTX 3090 24GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~176 tok/s | ollama run bonsai-2:9b |
| RTX 4090 24GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~189 tok/s | ollama run bonsai-2:9b |
| RX 7900 XTX 24GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~180 tok/s | ollama run bonsai-2:9b |
| M1 Pro 32GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~50 tok/s | ollama run bonsai-2:9b |
| M2 Pro 32GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~50 tok/s | ollama run bonsai-2:9b |
| M4 32GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~30 tok/s | ollama run bonsai-2:9b |
| M3 Pro 36GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~38 tok/s | ollama run bonsai-2:9b |
| Mac Studio M4 Max (32c GPU) 36GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~103 tok/s | ollama run bonsai-2:9b |
| Mac Studio M5 Max (32c GPU) 36GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~115 tok/s | ollama run bonsai-2:9b |
| RTX 5090 32GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~336 tok/s | ollama run bonsai-2:9b |
| M4 Pro 48GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~68 tok/s | ollama run bonsai-2:9b |
| Mac Studio M4 Max (40c GPU) 48GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~137 tok/s | ollama run bonsai-2:9b |
| Mac Studio M5 Max (40c GPU) 48GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~154 tok/s | ollama run bonsai-2:9b |
| M1 Max 64GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~100 tok/s | ollama run bonsai-2:9b |
| M2 Max 64GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~100 tok/s | ollama run bonsai-2:9b |
| M3 Max 64GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~100 tok/s | ollama run bonsai-2:9b |
| M4 Max 64GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~137 tok/s | ollama run bonsai-2:9b |
| Mac Studio M4 Max (40c GPU) 64GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~137 tok/s | ollama run bonsai-2:9b |
| Mac Studio M5 Max (40c GPU) 64GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~154 tok/s | ollama run bonsai-2:9b |
| DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~64 tok/s | ollama run bonsai-2:9b |
| Mac Studio M3 Ultra 96GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~205 tok/s | ollama run bonsai-2:9b |
| Mac Studio M5 Ultra 96GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~300 tok/s | ollama run bonsai-2:9b |
| M3 Max 128GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~100 tok/s | ollama run bonsai-2:9b |
| M4 Max 128GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~137 tok/s | ollama run bonsai-2:9b |
| Mac Studio M4 Max (40c GPU) 128GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~137 tok/s | ollama run bonsai-2:9b |
| Mac Studio M5 Max (40c GPU) 128GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~154 tok/s | ollama run bonsai-2:9b |
| DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~64 tok/s | ollama run bonsai-2:9b |
| M2 Ultra 192GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~200 tok/s | ollama run bonsai-2:9b |
| Mac Studio M3 Ultra 256GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~205 tok/s | ollama run bonsai-2:9b |
| Mac Studio M5 Ultra (64c GPU) 256GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~300 tok/s | ollama run bonsai-2:9b |
| Mac Studio M5 Ultra (80c GPU) 256GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~300 tok/s | ollama run bonsai-2:9b |
| Mac Studio M3 Ultra (80c GPU) 512GB | Ollama | Q2_0 | 4.6 GB | fits in fast memory | ~205 tok/s | ollama run bonsai-2:9b |
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 2026-10-18.
A project by OnDevice Labs · llms.txt