General model by voidful · 0.61B parameters · Released 2022-09-29
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
mbart large 50 many to many unit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 5% of your RAM.
Specifications
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.2 GB | ~264 tok/s | ✓ |
| Q6_K | 1.0 GB | ~346 tok/s | ✓ |
| Q5_K_M | 1.0 GB | ~407 tok/s | ✓ |
| Q4_K_M | 0.9 GB | ~477 tok/s | ✓ |
| Q3_K_M | 0.8 GB | ~577 tok/s | ✓ |
| Q2_K | 0.8 GB | ~748 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