Chat model by ath-maas · 8B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Marco Nano Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 39% of your RAM.
— tok/s
Q8_0 · 9.4 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 9.4 GB | ~184 tok/s | ✓ |
| Q6_K | 7.4 GB | ~241 tok/s | ✓ |
| Q5_K_M | 6.5 GB | ~284 tok/s | ✓ |
| Q4_K_M | 5.7 GB | ~333 tok/s | ✓ |
| Q3_K_M | 4.9 GB | ~402 tok/s | ✓ |
| Q2_K | 4.0 GB | ~521 tok/s | ✓ |
Affiliate disclosure: the shop icons in this table are Amazon affiliate links. As an Amazon Associate, ModelPiper earns from qualifying purchases. Every fit rating, quantization and tok/s figure below is computed from the hardware specs and is not influenced by that.
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper free