Chat model by TII · 3.15B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Falcon H1 3B Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 17% of your RAM.
~51 tok/s
Q8_0 · 4.0 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 4.0 GB | ~51 tok/s | ✓ |
| Q6_K | 3.2 GB | ~67 tok/s | ✓ |
| Q5_K_M | 2.8 GB | ~79 tok/s | ✓ |
| Q4_K_M | 2.5 GB | ~92 tok/s | ✓ |
| Q3_K_M | 2.2 GB | ~112 tok/s | ✓ |
| Q2_K | 1.9 GB | ~145 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