Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
77.1 tok/s
TTFT
2511 ms
Safe context
21K
Memory
9.3 GB / 12.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 77.1 tok/s | 3652 ms | 36K |
| Chat | B | Runs well | 77.1 tok/s | 1369 ms | 11K |
| Coding | B | Runs well | 77.1 tok/s | 2511 ms | 21K |
| RAG | C | Tight fit | 77.1 tok/s | 4565 ms | 36K |
| Reasoning | B | Runs well | 77.1 tok/s | 2967 ms | 21K |
How HelpingAI2 9B (9B params) fits at each quantization level on RTX 5070 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | D35 |
Q3_K_S | 3 | 4.4 GB | Low | D37 |
NVFP4 | 4 | 5.0 GB | Medium | D38 |
Q4_K_M | 4 | 5.5 GB | Medium | D39 |
Q5_K_M | 5 | 6.5 GB | High | C40 |
Q6_KBest for your GPU | 6 | 7.4 GB | High | C42 |
Q8_0 | 8 | 9.6 GB | Very High | C44 |
F16 | 16 | 18.5 GB | Maximum | F0 |
