 |
VOOZH | about |
Qwen 2.5 Math 72B needs ~52.3 GB but MacBook Pro M4 Pro 24GB only has 17.3 GB. Try a smaller quantization or lighter model.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
35.0 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
4.2 tok/s
TTFT
45920 ms
Safe context
4K
Memory
52.3 GB / 17.3 GB
Offload
70%
Usable shared or unified memory is the main blocker for this model.
Not enough usable memory
The model needs 52.3 GB, but this setup only exposes 17.3 GB of usable shared or unified memory.
Move to a larger memory pool
A larger unified-memory SKU or a discrete high-bandwidth GPU is the cleanest way to make this model practical.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 4.2 tok/s | 25047 ms | 4K |
| Coding | F | Too heavy | 4.2 tok/s | 45920 ms | 4K |
| Agentic Coding | F | Too heavy | 4.2 tok/s | 66792 ms | 4K |
| Reasoning | F | Too heavy | 4.2 tok/s | 54269 ms | 4K |
| RAG | F | Too heavy | 4.2 tok/s | 83491 ms | 4K |
How Qwen 2.5 Math 72B (72B params) fits at each quantization level on MacBook Pro M4 Pro 24GB (17.3 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 28.1 GB | Low | F0 |
Q3_K_S | 3 | 35.3 GB | Low | F0 |
NVFP4 | 4 | 40.3 GB | Medium | F0 |
Q4_K_M | 4 | 43.9 GB | Medium | F0 |
Q5_K_M | 5 | 51.8 GB | High | F0 |
Q6_K | 6 | 59.0 GB | High | F0 |
Q8_0 | 8 | 77.0 GB | Very High | F0 |
F16 | 16 | 147.6 GB | Maximum | F0 |
Upgrade options
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$2,499 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$2,499 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$3,199 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$40,000 MSRP
