Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
89.0 tok/s
TTFT
2176 ms
Safe context
23K
Memory
8.4 GB / 12.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 89.0 tok/s | 3165 ms | 40K |
| Chat | B | Runs well | 89.0 tok/s | 1187 ms | 12K |
| Coding | B | Runs well | 89.0 tok/s | 2176 ms | 23K |
| RAG | B | Runs well | 89.0 tok/s | 3956 ms | 40K |
| Reasoning | B | Runs well | 89.0 tok/s | 2571 ms | 23K |
How EXAONE 3.5 7.8B Instruct (7.800000190734863B params) fits at each quantization level on RTX 5070 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.0 GB | Low | D34 |
Q3_K_S | 3 | 3.8 GB | Low | D36 |
NVFP4 | 4 | 4.4 GB | Medium | D37 |
Q4_K_M | 4 | 4.8 GB | Medium | D38 |
Q5_K_M | 5 | 5.6 GB | High | D39 |
Q6_K | 6 | 6.4 GB | High | C40 |
Q8_0Best for your GPU | 8 | 8.3 GB | Very High | C44 |
F16 | 16 | 16.0 GB | Maximum | F0 |
