← CanIRunLocal · All hardware · All models
Mixedbread · 0.335B parameters · embedding.
Ollama weight files: FP16 0.67 GB (mxbai-embed-large:335m).
Yes on 58 machines in this list. The smallest is M1 8GB: FP16, about 0.9 GB, via Ollama. ollama pull mxbai-embed-large:335m
ollama pull mxbai-embed-large:335mollama pull mxbai-embed-large:335mollama pull mxbai-embed-large:335mollama pull mxbai-embed-large:335mvllm serve mixedbread-ai/mxbai-embed-large-v1 --task embed --gpu-memory-utilization 0.9| Hardware | Runtime | Quant | Memory | Fit | Use | Command |
|---|---|---|---|---|---|---|
| M1 8GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M2 8GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M3 8GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 3060 Ti 8GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 3070 8GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 4060 8GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RX 7600 8GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 3080 10GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M1 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M2 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M3 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M4 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 3060 12GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 4070 12GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 5070 12GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 4060 Ti 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 4070 Ti Super 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 4080 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 5080 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RX 7800 XT 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RX 9070 XT 16GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M2 24GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M3 24GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M4 24GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 3090 24GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 4090 24GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RX 7900 XTX 24GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M1 Pro 32GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M2 Pro 32GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M4 32GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M3 Pro 36GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M4 Max (32c GPU) 36GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M5 Max (32c GPU) 36GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| RTX 5090 32GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M4 Pro 48GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M4 Max (40c GPU) 48GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M5 Max (40c GPU) 48GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M1 Max 64GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M2 Max 64GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M3 Max 64GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M4 Max 64GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M4 Max (40c GPU) 64GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M5 Max (40c GPU) 64GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M3 Ultra 96GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M5 Ultra 96GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M3 Max 128GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M4 Max 128GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M4 Max (40c GPU) 128GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M5 Max (40c GPU) 128GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| M2 Ultra 192GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M3 Ultra 256GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M5 Ultra (64c GPU) 256GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| Mac Studio M5 Ultra (80c GPU) 256GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| 2x DGX Spark 128GB | vLLM | Official weights | 0.9 GB | fits in fast memory | embedding | vllm serve mixedbread-ai/mxbai-embed-large-v1 --tensor-parallel-size 2 --distributed-executor-backend ray --task embed |
| Mac Studio M3 Ultra (80c GPU) 512GB | Ollama | FP16 | 0.9 GB | fits in fast memory | embedding | ollama pull mxbai-embed-large:335m |
| 4x DGX Spark 128GB | vLLM | Official weights | 0.9 GB | fits in fast memory | embedding | vllm serve mixedbread-ai/mxbai-embed-large-v1 --tensor-parallel-size 4 --distributed-executor-backend ray --task embed |
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