With 16 GB of VRAM, the RTX 5060 Ti 16 GB runs Llama 3.2 1B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 2 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 2 GB and fits in the 15.5 GB available, with 13.5 GB to spare.
~2 GB (1.7 GB–2.3 GB) needed · estimate
Fits entirely in VRAM · 13.5 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Llama 3.2 1B Instruct Q8_08K~2.5 GB · 194–277 tok/s estimate | Excellent |
|---|---|
| Llama 3.2 1B Instruct Q6_K8K~2.2 GB · 233–341 tok/s estimate | Excellent |
| Llama 3.2 1B Instruct Q5_K_M8K~2.1 GB · 251–373 tok/s estimate | Excellent |
| Llama 3.2 1B Instruct Q4_K_M8K~2 GB · 272–408 tok/s estimate | Excellent |
| Llama 3.2 1B Instruct IQ4_XS8K~2 GB · 286–434 tok/s estimate | Excellent |
| Llama 3.2 1B Instruct Q3_K_M8K~1.9 GB · 299–458 tok/s estimate | Excellent |
Prices and links follow the market you choose.
16 GB GDDR7 · 448 GB/s · 180 W
ExcellentRuns Llama 3.2 1B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
