With 24 GB of VRAM, the RX 7900 XTX runs Qwen2.5 14B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 11.3 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 11.3 GB and fits in the 23.3 GB available, with 12 GB to spare.
~11.3 GB (10.7 GB–11.9 GB) needed · estimate
Fits entirely in VRAM · 12 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 · 34–50 tok/s estimate | Excellent |
|---|---|
| Qwen2.5 14B Instruct Q6_K8K~14.3 GB · 42–62 tok/s estimate | Excellent |
| Qwen2.5 14B Instruct Q5_K_M8K~12.8 GB · 47–69 tok/s estimate | Excellent |
| Qwen2.5 14B Instruct Q4_K_M8K~11.3 GB · 52–79 tok/s estimate | Excellent |
| Qwen2.5 14B Instruct IQ4_XS8K~10.4 GB · 56–85 tok/s estimate | Excellent |
| Qwen2.5 14B Instruct Q3_K_M8K~9.7 GB · 60–92 tok/s estimate | Excellent |
Prices and links follow the market you choose.
24 GB GDDR6 · 960 GB/s · 355 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.
