With 16 GB of VRAM, the RTX 4070 Ti SUPER runs DeepSeek R1 Distill Llama 8B at Q4_K_M entirely on the GPU with an 8K context (about 6.7 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 6.7 GB and fits in the 15.5 GB available, with 8.9 GB to spare.
~6.7 GB (6.2 GB–7.1 GB) needed · estimate
Fits entirely in VRAM · 8.9 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| DeepSeek R1 Distill Llama 8B Q8_08K~10.2 GB · 52–70 tok/s estimate | Excellent |
|---|---|
| DeepSeek R1 Distill Llama 8B Q6_K8K~8.3 GB · 64–88 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 8B Q5_K_M8K~7.5 GB · 71–99 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 8B Q4_K_M8K~6.7 GB · 80–113 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 8B IQ4_XS8K~6.2 GB · 87–123 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 8B Q3_K_M8K~5.8 GB · 94–133 tok/s estimate | Excellent |
Prices and links follow the market you choose.
16 GB GDDR6X · 672 GB/s · 285 W
ExcellentRuns DeepSeek R1 Distill Llama 8B Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
