General model by ib-ssm · 8.24B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
mamba2 8b 3t 4k hf fits comfortably in your 24 GB Mac using Q8_0 quantization, using 40% of your RAM.
~20 tok/s
Q8_0 · 9.7 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 9.7 GB | ~20 tok/s | ✓ |
| Q6_K | 7.6 GB | ~26 tok/s | ✓ |
| Q5_K_M | 6.6 GB | ~30 tok/s | ✓ |
| Q4_K_M | 5.8 GB | ~35 tok/s | ✓ |
| Q3_K_M | 5.0 GB | ~43 tok/s | ✓ |
| Q2_K | 4.1 GB | ~55 tok/s | ✓ |
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free