Chat model by allenai · 6.92B parameters
OLMoE 1B 7B 0125 Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 34% of your RAM.
~138 tok/s
Q8_0 · 8.2 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 8.2 GB | ~138 tok/s | ✓ |
| Q6_K | 6.5 GB | ~181 tok/s | ✓ |
| Q5_K_M | 5.7 GB | ~213 tok/s | ✓ |
| Q4_K_M | 5.0 GB | ~249 tok/s | ✓ |
| Q3_K_M | 4.3 GB | ~301 tok/s | ✓ |
| Q2_K | 3.5 GB | ~391 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free