Chat model by axou45 · 71.62B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
llama 31 70b instructiontuned uncensored merged requires 31.7 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 80.4 GB | ~2 tok/s | ✗ |
| Q6_K | 62.5 GB | ~3 tok/s | ✗ |
| Q5_K_M | 53.9 GB | ~3 tok/s | ✗ |
| Q4_K_M | 46.7 GB | ~4 tok/s | ✗ |
| Q3_K_M | 39.6 GB | ~5 tok/s | ✗ |
| Q2_K | 31.7 GB | ~6 tok/s | ✗ |
Affiliate disclosure: the shop icons in this table are Amazon affiliate links. As an Amazon Associate, ModelPiper earns from qualifying purchases. Every fit rating, quantization and tok/s figure below is computed from the hardware specs and is not influenced by that.
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper free