Can it run?
Runs well
Using F16 in Ollama
Fit status
Runs well
Decode
64.0 tok/s
TTFT
3025 ms
Safe context
8K
Memory
2.7 GB / 4.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 64.0 tok/s | 4400 ms | 8K |
| Chat | B | Runs well | 64.0 tok/s | 1650 ms | 8K |
| Coding | B | Runs well | 64.0 tok/s | 3025 ms | 8K |
| RAG | B | Runs well | 64.0 tok/s | 5500 ms | 8K |
| Reasoning | B | Runs well | 64.0 tok/s | 3575 ms | 8K |
How Jina Embeddings v3 (0.5720000267028809B params) fits at each quantization level on GTX 1650 4GB (4.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.2 GB | Low | D30 |
Q3_K_S | 3 | 0.3 GB | Low | D31 |
NVFP4 | 4 | 0.3 GB | Medium | D31 |
Q4_K_M | 4 | 0.3 GB | Medium | D31 |
Q5_K_M | 5 | 0.4 GB | High | D31 |
Q6_K | 6 | 0.5 GB | High | D32 |
Q8_0 | 8 | 0.6 GB | Very High | D32 |
F16Best for your GPU | 16 | 1.2 GB | Maximum | D36 |
ollama run jina-embeddings-v3huggingface-cli download jina-embeddings-v3