General model by jangq-ai · 21.76B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
DeepSeek V4 Flash JANGTQ K fits comfortably in your 24 GB Mac using Q6_K quantization, using 81% of your RAM.
Specifications
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 24.8 GB | ~114 tok/s | ✗ |
| Q6_K Recommended | 19.3 GB | ~150 tok/s | ✓ |
| Q5_K_M | 16.7 GB | ~176 tok/s | ✓ |
| Q4_K_M | 14.5 GB | ~206 tok/s | ✓ |
| Q3_K_M | 12.4 GB | ~249 tok/s | ✓ |
| Q2_K | 10.0 GB | ~323 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