Chat model by Community · 1.1B parameters · Released 2023-12-30
TinyLlama 1.1B Chat v1.0 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 7% of your RAM.
~146 tok/s
Q8_0 · 1.7 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.7 GB | ~146 tok/s | ✓ |
| Q6_K | 1.5 GB | ~192 tok/s | ✓ |
| Q5_K_M | 1.3 GB | ~226 tok/s | ✓ |
| Q4_K_M | 1.2 GB | ~265 tok/s | ✓ |
| Q3_K_M | 1.1 GB | ~320 tok/s | ✓ |
| Q2_K | 1.0 GB | ~415 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free