With 16 GB of VRAM, the RTX 5060 Ti 16 GB runs Qwen3.5 9B at Q4_K_M entirely on the GPU with an 8K context (about 6.9 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 6.9 GB and fits in the 15.5 GB available, with 8.6 GB to spare.
~6.9 GB (6.4 GB–7.4 GB) needed · estimate
Fits entirely in VRAM · 8.6 GB left
EstimateData updated 40 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Qwen3.5 9B Q8_08K~10.7 GB · 33–44 tok/s estimate | Excellent |
|---|---|
| Qwen3.5 9B Q6_K8K~8.6 GB · 42–56 tok/s estimate | Excellent |
| Qwen3.5 9B Q5_K_M8K~7.8 GB · 47–63 tok/s estimate | Excellent |
| Qwen3.5 9B Q4_K_M8K~6.9 GB · 53–72 tok/s estimate | Excellent |
| Qwen3.5 9B IQ4_XS8K~6.4 GB · 58–79 tok/s estimate | Excellent |
| Qwen3.5 9B Q3_K_M8K~5.9 GB · 63–86 tok/s estimate | Excellent |
Prices and links follow the market you choose.
16 GB GDDR7 · 448 GB/s · 180 W
ExcellentRuns Qwen3.5 9B Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
