Can the RTX 5060 run Qwen2.5-Coder-14B-Instruct?
No. Qwen2.5-Coder-14B-Instruct needs about 10.8 GB at Q4_K_M (weights plus 1.8 GB runtime overhead), and the RTX 5060 has 8 GB, so it won't fit without offloading layers to system RAM, which is far slower.
Every quantization
Qwen2.5-Coder-14B-Instruct (14.8B) on 8 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 9 GB | 10.8 GB | Too big | - |
| Q5_K_M | 11 GB | 12.8 GB | Too big | - |
| Q8_0 | 16 GB | 17.8 GB | Too big | - |
| FP16 | 30 GB | 31.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 5060's 448 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
What to do instead
Two ways forward
Cheapest cards that run it
- NVIDIA Tesla P40 - 24 GB, ~$159
- NVIDIA RTX 3060 12GB - 12 GB, ~$199
- Intel Arc A770 16GB - 16 GB, ~$229
- Intel Arc B580 - 12 GB, ~$249
Models that fit the RTX 5060
- Mistral-7B-Instruct-v0.2 - 7.2B, 4 GB at Q4
- Qwen3.5 4B - 4.7B, 3 GB at Q4
- Qwen3-4B-Instruct-2507 - 4B, 2 GB at Q4
- NVIDIA Nemotron 3 Nano 4B - 4B, 2 GB at Q4
Compare
Same model, other hardware - and other models on this card
Qwen2.5-Coder-14B-Instruct on other hardware
- RTX 5090~114 tok/s
- RTX 5090 D~114 tok/s
- RTX 6000D~100 tok/s
- RTX 4090~70 tok/s
- RTX 3090~61 tok/s
- Radeon RX 7900 XTX~61 tok/s
- RTX 5080~61 tok/s
- RTX 3080 Ti~58 tok/s
Also runs on the RTX 5060
- Mistral-7B-Instruct-v0.2~64 tok/s
- Qwen3.5 4B~86 tok/s
- Qwen3-4B-Instruct-2507~128 tok/s
- NVIDIA Nemotron 3 Nano 4B~128 tok/s
- Phi-4 Mini~103 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX 5060 run Qwen2.5-Coder-14B-Instruct?
No. Qwen2.5-Coder-14B-Instruct needs about 10.8 GB at Q4_K_M (weights plus 1.8 GB runtime overhead), and the RTX 5060 has 8 GB, so it won't fit without offloading layers to system RAM, which is far slower.
How much VRAM does Qwen2.5-Coder-14B-Instruct need?
About 9 GB of weights at Q4_K_M, 16 GB at Q8_0 and 30 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Qwen2.5-Coder-14B-Instruct on the RTX 5060?
It doesn't fit in the RTX 5060's memory, so speed depends on how many layers you offload to system RAM - typically single-digit tokens per second or lower.