General model by cerebras · 23B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro, Mac mini M5 Pro
GLM 4.7 Flash REAP 23B A3B can run but will be tight at 85% of RAM. Consider a lower quantization or closing other apps.
Alternative: Q5_K_M (17.6 GB, ~84 tok/s)
Specifications
GGUF Sources
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 26.2 GB | ~54 tok/s | ✗ |
| Q6_K Recommended | 20.4 GB | ~71 tok/s | ✓ |
| Q5_K_M | 17.6 GB | ~84 tok/s | ✓ |
| Q4_K_M | 15.3 GB | ~98 tok/s | ✓ |
| Q3_K_M | 13.0 GB | ~118 tok/s | ✓ |
| Q2_K | 10.5 GB | ~154 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