Can it run?
Runs well
Using F16 in Ollama
Fit status
Runs well
Decode
92.2 tok/s
TTFT
2101 ms
Safe context
512
Memory
2.6 GB / 4.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 64.0 tok/s | 4400 ms | 512 |
| Chat | C | Runs well | 64.0 tok/s | 1650 ms | 512 |
| Coding | B | Runs well | 92.2 tok/s | 2101 ms | 512 |
| RAG | C | Runs well | 64.0 tok/s | 5500 ms | 512 |
| Reasoning | C | Runs well | 64.0 tok/s | 3575 ms | 512 |
How mxbai Embed Large (0.33500000834465027B params) fits at each quantization level on GTX 1650 4GB (4.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.1 GB | Low | D30 |
Q3_K_S | 3 | 0.2 GB | Low | D30 |
NVFP4 | 4 |
ollama run mxbai-embed-largehuggingface-cli download mxbai-embed-large| Medium |
| D30 |
Q4_K_M | 4 | 0.2 GB | Medium | D30 |
Q5_K_M | 5 | 0.2 GB | High | D30 |
Q6_K | 6 | 0.3 GB | High | D31 |
Q8_0 | 8 | 0.4 GB | Very High | D31 |
F16Best for your GPU | 16 | 0.7 GB | Maximum | D33 |