With 8 GB of VRAM, the RTX 4060 Ti 8 GB 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 does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 6.7 GB and fits in the 7.7 GB available (1 GB left).
~6.7 GB (6.2 GB–7.1 GB) needed · estimate
Fits entirely in VRAM · 1 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 · 6.5–12 tok/s estimate | CPU/GPU offload |
|---|---|
| DeepSeek R1 Distill Llama 8B Q6_K8K~8.3 GB · 15–26 tok/s estimate | CPU/GPU offload |
| DeepSeek R1 Distill Llama 8B Q5_K_M8K~7.5 GB · 33–44 tok/s estimate | Compatible with limits |
| DeepSeek R1 Distill Llama 8B Q4_K_M8K~6.7 GB · 38–50 tok/s estimate | Compatible |
| DeepSeek R1 Distill Llama 8B IQ4_XS8K~6.2 GB · 41–55 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 8B Q3_K_M8K~5.8 GB · 45–60 tok/s estimate | Excellent |
Prices and links follow the market you choose.
8 GB GDDR6 · 288 GB/s · 160 W
CompatibleRuns DeepSeek R1 Distill Llama 8B Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
