Can it run?
Runs well
Using Q5_K_M in Ollama
Fit status
Runs well
Decode
65.3 tok/s
TTFT
2966 ms
Safe context
8K
Memory
16.7 GB / 24.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 65.3 tok/s | 4314 ms | 8K |
| Chat | C | Runs well | 65.3 tok/s | 1618 ms | 8K |
| Coding | B | Runs well | 65.3 tok/s | 2966 ms | 8K |
| RAG | B | Runs well | 65.3 tok/s | 5392 ms | 8K |
| Reasoning | B | Runs well | 65.3 tok/s | 3505 ms | 8K |
How StarCoder 15B (15B params) fits at each quantization level on RX 7900 XTX 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | D35 |
Q3_K_S | 3 | 7.4 GB | Low | D36 |
NVFP4 | 4 | 8.4 GB | Medium | D37 |
Q4_K_M | 4 | 9.2 GB | Medium | D38 |
Q5_K_M | 5 | 10.8 GB | High | D39 |
Q6_K | 6 | 12.3 GB | High | C40 |
Q8_0Best for your GPU | 8 | 16.1 GB | Very High | C44 |
F16 | 16 | 30.7 GB | Maximum | F0 |
ollama run starcoder-15bhuggingface-cli download starcoder-15b