Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
172.3 tok/s
TTFT
1124 ms
Safe context
73K
Memory
10.1 GB / 46.1 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 172.3 tok/s | 1634 ms | 146K |
| Chat | C | Runs well | 172.3 tok/s | 613 ms | 36K |
| Coding | C | Runs well | 172.3 tok/s | 1124 ms | 73K |
| RAG | C | Runs well | 172.3 tok/s | 2043 ms | 146K |
| Reasoning | C | Runs well | 172.3 tok/s | 1328 ms | 73K |
How gemma 2b (2B params) fits at each quantization level on MacBook Pro M4 Pro 64GB (46.1 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.8 GB | Low | D30 |
Q3_K_S | 3 | 1.0 GB | Low | D30 |
NVFP4 | 4 | 1.1 GB | Medium | D30 |
Q4_K_M | 4 | 1.2 GB | Medium | D30 |
Q5_K_M | 5 | 1.4 GB | High | D30 |
Q6_K | 6 | 1.6 GB | High | D30 |
Q8_0 | 8 | 2.1 GB | Very High | D31 |
F16Best for your GPU | 16 | 4.1 GB | Maximum | D31 |
