Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
135.3 tok/s
TTFT
1431 ms
Safe context
4K
Memory
7.6 GB / 10.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 135.3 tok/s | 2082 ms | 4K |
| Chat | B | Runs well | 135.3 tok/s | 781 ms | 4K |
| Coding | B | Runs well | 135.3 tok/s | 1431 ms | 4K |
| RAG | C | Tight fit | 135.3 tok/s | 2602 ms | 4K |
| Reasoning | B | Runs well | 135.3 tok/s | 1691 ms | 4K |
How WizardMath 7B (7B params) fits at each quantization level on RTX 3080 10GB (10.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | D34 |
Q3_K_S | 3 | 3.4 GB | Low | D36 |
NVFP4 | 4 | 3.9 GB | Medium | D37 |
Q4_K_M | 4 | 4.3 GB | Medium | D38 |
Q5_K_M | 5 | 5.0 GB | High | D39 |
Q6_KBest for your GPU | 6 | 5.7 GB | High | C41 |
Q8_0 | 8 | 7.5 GB | Very High | C44 |
F16 | 16 | 14.3 GB | Maximum | F0 |
ollama run wizard-math-7bhuggingface-cli download wizard-math-7b