General model by jackfram · 0.04B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
llama 68m fits comfortably in your 24 GB Mac using Q8_0 quantization, using 2% of your RAM.
~4,020 tok/s
Q8_0 · 0.5 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 0.5 GB | ~4,020 tok/s | ✓ |
| Q6_K | 0.5 GB | ~5,277 tok/s | ✓ |
| Q5_K_M | 0.5 GB | ~6,208 tok/s | ✓ |
| Q4_K_M | 0.5 GB | ~7,278 tok/s | ✓ |
| Q3_K_M | 0.5 GB | ~8,794 tok/s | ✓ |
| Q2_K | 0.5 GB | ~11,409 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