GPUs & Macs › Nvidia Tesla K40
Nvidia Tesla K40: local LLM speed
Llama 2 7B (Q4_0) generates 9.9 tokens/s on the Nvidia Tesla K40 (Vulkan), and processes prompts at 64 tokens/s.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 2 7B | 9.9 | 64 | Q4_0 | Vulkan FA on | tg128 | llama.cpp #10879 details |
| Llama 2 7B | 9.3 | 64 | Q4_0 | Vulkan FA off | tg128 | llama.cpp #10879 details |
What fits on the Nvidia Tesla K40
Estimates for this chip are scaled from a measured run: Llama 2 7B Q4_0 at 9.9 tok/s (Vulkan, source). Fit assumes the whole model in GPU memory with ~8K context.
Memory size unknown for this device.
Similar hardware
Nvidia A100 · Nvidia Tesla T10 · NVIDIA Quadro P620 · NVIDIA GT 1030 · NVIDIA MX150 · NVIDIA GTX 980 · NVIDIA GTX 1050 Ti · NVIDIA GTX 1650 Ti