RX 7900 XTX 24GBBest value
C96.1 tok/s decode
~$999 MSRP
Can it run?
Runs with offload
Using Q4_K_M in Ollama
Fit status
Runs with offload
Decode
35.7 tok/s
TTFT
5424 ms
Safe context
15K
Memory
24.1 GB / 23.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs with offload (needs ~1 GB host RAM) | 30.1 tok/s | 9350 ms | 30K |
| Chat | C | Runs with offload (needs ~0.8 GB host RAM) | 30.2 tok/s | 3497 ms | 8K |
| Coding | C | Runs with offload | 35.7 tok/s | 5424 ms | 15K |
| RAG | C | Runs with offload (needs ~1 GB host RAM) | 30.1 tok/s | 11688 ms | 30K |
| Reasoning | C | Runs with offload (needs ~0.8 GB host RAM) | 30.2 tok/s |
How Qwen3-Coder 30B A3B Instruct (30.5B params) fits at each quantization level on MacBook Pro M1 Max 32GB (23.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 11.9 GB | Low | C41 |
Q3_K_S | 3 | 14.9 GB | Low | C43 |
NVFP4Best for your GPU |
ollama run qwen-3-coder-30b-a3bhuggingface-cli download qwen-3-coder-30b-a3bUpgrade options
~$999 MSRP
~$1,599 MSRP
| 7576 ms |
| 15K |
| 4 |
17.1 GB |
| Medium |
| C45 |
Q4_K_M | 4 | 18.6 GB | Medium | C45 |
Q5_K_M | 5 | 22.0 GB | High | C45 |
Q6_K | 6 | 25.0 GB | High | F0 |
Q8_0 | 8 | 32.6 GB | Very High | F0 |
F16 | 16 | 62.5 GB | Maximum | F0 |
~$2,499 MSRP