With 8 GB of VRAM, the RTX 5060 runs Qwen2.5 7B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 5.9 GB needed). At Q8_0 it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 5.9 GB and fits in the 7.7 GB available, with 1.8 GB to spare.
~5.9 GB (5.5 GB–6.3 GB) needed · estimate
Fits entirely in VRAM · 1.8 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 7B Instruct Q8_08K~9.2 GB · 10–19 tok/s estimate | CPU/GPU offload |
|---|---|
| Qwen2.5 7B Instruct Q6_K8K~7.4 GB · 49–66 tok/s estimate | Compatible with limits |
| Qwen2.5 7B Instruct Q5_K_M8K~6.6 GB · 55–75 tok/s estimate | Compatible |
| Qwen2.5 7B Instruct Q4_K_M8K~5.9 GB · 63–86 tok/s estimate | Excellent |
| Qwen2.5 7B Instruct IQ4_XS8K~5.5 GB · 69–94 tok/s estimate | Excellent |
| Qwen2.5 7B Instruct Q3_K_M8K~5.1 GB · 75–103 tok/s estimate | Excellent |
Prices and links follow the market you choose.
8 GB GDDR7 · 448 GB/s · 145 W
ExcellentRuns Qwen2.5 7B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
