With 16 GB of VRAM, the RTX 5080 runs Qwen2.5 14B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 11.2 GB needed). At Q8_0 it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 11.2 GB and fits in the 15.5 GB available, with 4.3 GB to spare.
~11.2 GB (10.7 GB–11.8 GB) needed · estimate
Fits entirely in VRAM · 4.3 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Qwen2.5 14B Instruct Q8_08K~17.8 GB · 7.5–14 tok/s estimate | CPU/GPU offload |
|---|---|
| Qwen2.5 14B Instruct Q6_K8K~14.3 GB · 49–69 tok/s estimate | Compatible |
| Qwen2.5 14B Instruct Q5_K_M8K~12.7 GB · 55–78 tok/s estimate | Excellent |
| Qwen2.5 14B Instruct Q4_K_M8K~11.2 GB · 62–89 tok/s estimate | Excellent |
| Qwen2.5 14B Instruct IQ4_XS8K~10.4 GB · 67–96 tok/s estimate | Excellent |
| Qwen2.5 14B Instruct Q3_K_M8K~9.6 GB · 72–105 tok/s estimate | Excellent |
Prices and links follow the market you choose.
16 GB GDDR7 · 960 GB/s · 360 W
ExcellentRuns Qwen2.5 14B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
