With 48 GB of VRAM, the RTX 6000 Ada 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 46.6 GB available, with 44.5 GB to spare.
~2 GB (1.7 GB–2.3 GB) needed · estimate
Fits entirely in VRAM · 44.5 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 · 342–539 tok/s estimate | Excellent |
|---|---|
| Llama 3.2 1B Instruct Q6_K8K~2.2 GB · 397–650 tok/s estimate | Excellent |
| Llama 3.2 1B Instruct Q5_K_M8K~2.1 GB · 422–703 tok/s estimate | Excellent |
| Llama 3.2 1B Instruct Q4_K_M8K~2 GB · 449–761 tok/s estimate | Excellent |
| Llama 3.2 1B Instruct IQ4_XS8K~2 GB · 467–803 tok/s estimate | Excellent |
| Llama 3.2 1B Instruct Q3_K_M8K~1.9 GB · 483–840 tok/s estimate | Excellent |
Prices and links follow the market you choose.
48 GB GDDR6 ECC · 960 GB/s · 300 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.
