Can it run?
Runs well
Using Q4_K_M in llama.cpp
Fit status
Runs well
Decode
72.3 tok/s
TTFT
2677 ms
Safe context
21K
Memory
12.5 GB / 16.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 72.3 tok/s | 3894 ms | 33K |
| Chat | B | Runs well | 72.3 tok/s | 1460 ms | 11K |
| Coding | B | Runs well | 72.3 tok/s | 2677 ms | 21K |
| RAG | C | Tight fit | 72.3 tok/s | 4868 ms | 33K |
| Reasoning | B | Runs well | 72.3 tok/s | 3164 ms | 21K |
How OLMo 2 13B (13B params) fits at each quantization level on RTX 5070 Ti 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | D36 |
Q3_K_S | 3 | 6.4 GB | Low | D37 |
NVFP4 | 4 | 7.3 GB | Medium | D39 |
Q4_K_M | 4 | 7.9 GB | Medium | D39 |
Q5_K_M | 5 | 9.4 GB | High | C41 |
Q6_KBest for your GPU | 6 | 10.7 GB | High | C43 |
Q8_0 | 8 | 13.9 GB | Very High | C44 |
F16 | 16 | 26.7 GB | Maximum | F0 |
huggingface-cli download olmo-2-13b