MacBook Pro M4 Max 36GBBudget pick
C105.9 tok/s decode
~$2,499 MSRP
Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
226.6 tok/s
TTFT
854 ms
Safe context
56K
Memory
6.8 GB / 24.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 245.5 tok/s | 1147 ms | 105K |
| Chat | C | Runs well | 245.5 tok/s | 430 ms | 28K |
| Coding | C | Runs well | 226.6 tok/s | 854 ms | 56K |
| RAG | C | Runs well | 245.5 tok/s | 1434 ms | 105K |
| Reasoning | C | Runs well | 245.5 tok/s | 932 ms | 56K |
How Qwen3.5 4B (4B params) fits at each quantization level on RTX A5500 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.6 GB | Low | D31 |
Q3_K_S | 3 | 2.0 GB | Low | D31 |
NVFP4 | 4 |
Upgrade options
~$2,499 MSRP
2.2 GB |
| Medium |
| D31 |
Q4_K_M | 4 | 2.4 GB | Medium | D32 |
Q5_K_M | 5 | 2.9 GB | High | D32 |
Q6_K | 6 | 3.3 GB | High | D32 |
Q8_0 | 8 | 4.3 GB | Very High | D33 |
F16Best for your GPU | 16 | 8.2 GB | Maximum | D37 |