Multimodal model by davidau · 12.19B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
gemma 3 12b it vl Polaris GLM 4.7 Flash VAR Thinking Instruct Heretic Uncensored fits comfortably in your 24 GB Mac using Q8_0 quantization, using 59% of your RAM.
~13 tok/s
Q8_0 · 14.1 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 14.1 GB | ~13 tok/s | ✓ |
| Q6_K | 11.1 GB | ~17 tok/s | ✓ |
| Q5_K_M | 9.6 GB | ~20 tok/s | ✓ |
| Q4_K_M | 8.4 GB | ~24 tok/s | ✓ |
| Q3_K_M | 7.2 GB | ~29 tok/s | ✓ |
| Q2_K | 5.8 GB | ~37 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