Chat model by meditsolutions · 7.65B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune fits comfortably in your 24 GB Mac using Q8_0 quantization, using 38% of your RAM.
~21 tok/s
Q8_0 · 9.0 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 9.0 GB | ~21 tok/s | ✓ |
| Q6_K | 7.1 GB | ~28 tok/s | ✓ |
| Q5_K_M | 6.2 GB | ~32 tok/s | ✓ |
| Q4_K_M | 5.4 GB | ~38 tok/s | ✓ |
| Q3_K_M | 4.7 GB | ~46 tok/s | ✓ |
| Q2_K | 3.8 GB | ~60 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