← CanIRunLocal · All hardware · All models
OpenBMB · 1.3B parameters · vision, chat.
Ollama weight files: Q4_K_M 1.6 GB (minicpm-v4.6:1b); Q5_K_M 1.7 GB (minicpm-v4.6:q5_K_M); Q8_0 1.9 GB (minicpm-v4.6:q8_0).
Yes on 58 machines in this list. The smallest is M1 8GB: Q8_0, about 2.9 GB, roughly 29 tokens per second, via Ollama. ollama run minicpm-v4.6:q8_0
ollama run minicpm-v4.6:q8_0ollama run minicpm-v4.6:q8_0ollama run minicpm-v4.6:q8_0ollama run minicpm-v4.6:q8_0vllm serve openbmb/MiniCPM-V-4_6 --max-model-len 8192 --gpu-memory-utilization 0.9| Hardware | Runtime | Quant | Memory | Fit | Speed | Command |
|---|---|---|---|---|---|---|
| M1 8GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~29 tok/s | ollama run minicpm-v4.6:q8_0 |
| M2 8GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~42 tok/s | ollama run minicpm-v4.6:q8_0 |
| M3 8GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~42 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 3060 Ti 8GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~141 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 3070 8GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~141 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 4060 8GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~86 tok/s | ollama run minicpm-v4.6:q8_0 |
| RX 7600 8GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~91 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 3080 10GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~240 tok/s | ollama run minicpm-v4.6:q8_0 |
| M1 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~29 tok/s | ollama run minicpm-v4.6:q8_0 |
| M2 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~42 tok/s | ollama run minicpm-v4.6:q8_0 |
| M3 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~42 tok/s | ollama run minicpm-v4.6:q8_0 |
| M4 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~51 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 3060 12GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~114 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 4070 12GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~159 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 5070 12GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~212 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 4060 Ti 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~91 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 4070 Ti Super 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~212 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 4080 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~226 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 5080 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~303 tok/s | ollama run minicpm-v4.6:q8_0 |
| RX 7800 XT 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~197 tok/s | ollama run minicpm-v4.6:q8_0 |
| RX 9070 XT 16GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~202 tok/s | ollama run minicpm-v4.6:q8_0 |
| M2 24GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~42 tok/s | ollama run minicpm-v4.6:q8_0 |
| M3 24GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~42 tok/s | ollama run minicpm-v4.6:q8_0 |
| M4 24GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~51 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 3090 24GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~296 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 4090 24GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~318 tok/s | ollama run minicpm-v4.6:q8_0 |
| RX 7900 XTX 24GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~303 tok/s | ollama run minicpm-v4.6:q8_0 |
| M1 Pro 32GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~84 tok/s | ollama run minicpm-v4.6:q8_0 |
| M2 Pro 32GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~84 tok/s | ollama run minicpm-v4.6:q8_0 |
| M4 32GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~51 tok/s | ollama run minicpm-v4.6:q8_0 |
| M3 Pro 36GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~63 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M4 Max (32c GPU) 36GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~173 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M5 Max (32c GPU) 36GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~194 tok/s | ollama run minicpm-v4.6:q8_0 |
| RTX 5090 32GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~566 tok/s | ollama run minicpm-v4.6:q8_0 |
| M4 Pro 48GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~115 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M4 Max (40c GPU) 48GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~230 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M5 Max (40c GPU) 48GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~259 tok/s | ollama run minicpm-v4.6:q8_0 |
| M1 Max 64GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~168 tok/s | ollama run minicpm-v4.6:q8_0 |
| M2 Max 64GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~168 tok/s | ollama run minicpm-v4.6:q8_0 |
| M3 Max 64GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~168 tok/s | ollama run minicpm-v4.6:q8_0 |
| M4 Max 64GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~230 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M4 Max (40c GPU) 64GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~230 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M5 Max (40c GPU) 64GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~259 tok/s | ollama run minicpm-v4.6:q8_0 |
| DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~108 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M3 Ultra 96GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~345 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M5 Ultra 96GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~505 tok/s | ollama run minicpm-v4.6:q8_0 |
| M3 Max 128GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~168 tok/s | ollama run minicpm-v4.6:q8_0 |
| M4 Max 128GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~230 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M4 Max (40c GPU) 128GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~230 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M5 Max (40c GPU) 128GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~259 tok/s | ollama run minicpm-v4.6:q8_0 |
| DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~108 tok/s | ollama run minicpm-v4.6:q8_0 |
| M2 Ultra 192GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~337 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M3 Ultra 256GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~345 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M5 Ultra (64c GPU) 256GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~505 tok/s | ollama run minicpm-v4.6:q8_0 |
| Mac Studio M5 Ultra (80c GPU) 256GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~505 tok/s | ollama run minicpm-v4.6:q8_0 |
| 2x DGX Spark 128GB | vLLM | Official weights | 3.6 GB | fits in fast memory | ~98 tok/s | vllm serve openbmb/MiniCPM-V-4_6 --tensor-parallel-size 2 --distributed-executor-backend ray --max-model-len 8192 |
| Mac Studio M3 Ultra (80c GPU) 512GB | Ollama | Q8_0 | 2.9 GB | fits in fast memory | ~345 tok/s | ollama run minicpm-v4.6:q8_0 |
| 4x DGX Spark 128GB | vLLM | Official weights | 3.6 GB | fits in fast memory | ~142 tok/s | vllm serve openbmb/MiniCPM-V-4_6 --tensor-parallel-size 4 --distributed-executor-backend ray --max-model-len 8192 |
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