Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
151.5 tok/s
TTFT
1278 ms
Safe context
25K
Memory
3.8 GB / 6.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 151.5 tok/s | 1859 ms | 50K |
| Chat | B | Runs well | 151.5 tok/s | 697 ms | 13K |
| Coding | B | Runs well | 151.5 tok/s | 1278 ms | 25K |
| RAG | B | Runs well | 151.5 tok/s | 2324 ms | 50K |
| Reasoning | B | Runs well | 151.5 tok/s | 1510 ms | 25K |
How gemma 2b (2B params) fits at each quantization level on GTX 1660 Super 6GB (6.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.8 GB | Low | D32 |
Q3_K_S | 3 | 1.0 GB | Low | D33 |
NVFP4 | 4 | 1.1 GB | Medium | D33 |
Q4_K_M | 4 | 1.2 GB | Medium | D34 |
Q5_K_M | 5 | 1.4 GB | High | D35 |
Q6_K | 6 | 1.6 GB | High | D35 |
Q8_0Best for your GPU | 8 | 2.1 GB | Very High | D37 |
F16 | 16 | 4.1 GB | Maximum | C44 |
