With 24 GB of VRAM, the Tesla P40 runs Llama 3.1 8B Instruct 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 23.3 GB available, with 16.6 GB to spare.
~6.7 GB (6.2 GB–7.1 GB) needed · estimate
Fits entirely in VRAM · 16.6 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Llama 3.1 8B Instruct Q8_08K~10.2 GB · 28–37 tok/s estimate | Excellent |
|---|---|
| Llama 3.1 8B Instruct Q6_K8K~8.3 GB · 35–46 tok/s estimate | Excellent |
| Llama 3.1 8B Instruct Q5_K_M8K~7.5 GB · 39–53 tok/s estimate | Excellent |
| Llama 3.1 8B Instruct Q4_K_M8K~6.7 GB · 45–60 tok/s estimate | Excellent |
| Llama 3.1 8B Instruct IQ4_XS8K~6.2 GB · 49–66 tok/s estimate | Excellent |
| Llama 3.1 8B Instruct Q3_K_M8K~5.8 GB · 53–72 tok/s estimate | Excellent |
Prices and links follow the market you choose.
NVIDIA
CompatibleRuns Llama 3.1 8B Instruct Q4_K_M entirely in memory
AMD
ExcellentRuns Llama 3.1 8B Instruct Q4_K_M entirely in memory
Unified memory PC
ExcellentRuns Llama 3.1 8B Instruct Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
