Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
115.0 tok/s
TTFT
1683 ms
Safe context
20K
Memory
8.2 GB / 10.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 115.0 tok/s | 2449 ms | 34K |
| Chat | B | Runs well | 115.0 tok/s | 918 ms | 10K |
| Coding | B | Runs well | 115.0 tok/s | 1683 ms | 20K |
| RAG | C | Tight fit | 115.0 tok/s | 3061 ms | 34K |
| Reasoning | B | Runs well | 115.0 tok/s | 1989 ms | 20K |
How exaone 3.0 7.8b it (7.800000190734863B params) fits at each quantization level on RTX 3080 10GB (10.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.0 GB | Low | D35 |
Q3_K_S | 3 | 3.8 GB | Low | D37 |
NVFP4 | 4 |
| Medium |
| D38 |
Q4_K_M | 4 | 4.8 GB | Medium | D39 |
Q5_K_M | 5 | 5.6 GB | High | C41 |
Q6_KBest for your GPU | 6 | 6.4 GB | High | C43 |
Q8_0 | 8 | 8.3 GB | Very High | C44 |
F16 | 16 | 16.0 GB | Maximum | F0 |