MacBook Pro M4 32GBBudget pick
C9.4 tok/s decode
~$799 MSRP
Can it run?
Tight fit
Using Q4_K_M in Ollama
Fit status
Tight fit
Decode
18.3 tok/s
TTFT
10605 ms
Safe context
18K
Memory
14.3 GB / 16.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs with offload (needs ~0.4 GB host RAM) | 17.7 tok/s | 15945 ms | 31K |
| Chat | C | Tight fit | 18.3 tok/s | 5784 ms | 10K |
| Coding | C | Tight fit | 18.3 tok/s | 10605 ms | 18K |
| RAG | C | Runs with offload (needs ~0.4 GB host RAM) | 17.7 tok/s | 19931 ms | 31K |
| Reasoning | C | Tight fit | 18.3 tok/s | 12533 ms | 18K |
How starcoder2 15b instruct v0.1 (15B params) fits at each quantization level on RX 7600 XT 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | D37 |
Q3_K_S | 3 | 7.4 GB | Low | D39 |
NVFP4 | 4 | 8.4 GB | Medium | C40 |
Q4_K_M | 4 | 9.2 GB | Medium | C41 |
Q5_K_MBest for your GPU | 5 | 10.8 GB | High | C43 |
Q6_K | 6 | 12.3 GB | High | C44 |
Q8_0 | 8 | 16.1 GB | Very High | F0 |
F16 | 16 | 30.7 GB | Maximum | F0 |
Upgrade options
~$799 MSRP
~$899 MSRP
~$999 MSRP
RTX A4500 20GBBiggest leap