Chat model by bsc-lt · 2.25B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
salamandra 2b instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 13% of your RAM.
~71 tok/s
Q8_0 · 3.0 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 3.0 GB | ~71 tok/s | ✓ |
| Q6_K | 2.4 GB | ~94 tok/s | ✓ |
| Q5_K_M | 2.2 GB | ~110 tok/s | ✓ |
| Q4_K_M | 2.0 GB | ~129 tok/s | ✓ |
| Q3_K_M | 1.7 GB | ~156 tok/s | ✓ |
| Q2_K | 1.5 GB | ~203 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