General model by nvidia · 0.65B parameters · Released 2024-05-29
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
C RADIO fits comfortably in your 24 GB Mac using Q8_0 quantization, using 5% of your RAM.
~247 tok/s
Q8_0 · 1.2 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.2 GB | ~247 tok/s | ✓ |
| Q6_K | 1.1 GB | ~325 tok/s | ✓ |
| Q5_K_M | 1.0 GB | ~382 tok/s | ✓ |
| Q4_K_M | 0.9 GB | ~448 tok/s | ✓ |
| Q3_K_M | 0.9 GB | ~541 tok/s | ✓ |
| Q2_K | 0.8 GB | ~702 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