Chat model by ibm-granite · 3.3B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
granite 3.1 3b a800m instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 17% of your RAM.
— tok/s
Q8_0 · 4.2 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 4.2 GB | ~203 tok/s | ✓ |
| Q6_K | 3.4 GB | ~267 tok/s | ✓ |
| Q5_K_M | 3.0 GB | ~314 tok/s | ✓ |
| Q4_K_M | 2.6 GB | ~368 tok/s | ✓ |
| Q3_K_M | 2.3 GB | ~444 tok/s | ✓ |
| Q2_K | 1.9 GB | ~576 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free