GPUs & Macs › Nvidia Tesla T10
Nvidia Tesla T10: local LLM speed
Llama 2 7B (Q4_0) generates 76.0 tokens/s on the Nvidia Tesla T10 (Vulkan), and processes prompts at 1,840 tokens/s.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 2 7B | 76.0 | 1,840 | Q4_0 | Vulkan FA on | tg128 | llama.cpp #10879 details |
| Llama 2 7B | 75.0 | 1,693 | Q4_0 | Vulkan FA off | tg128 | llama.cpp #10879 details |
What fits on the Nvidia Tesla T10
Estimates for this chip are scaled from a measured run: Llama 2 7B Q4_0 at 76.0 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 K40 · NVIDIA Quadro P620 · NVIDIA GT 1030 · NVIDIA MX150 · NVIDIA GTX 980 · NVIDIA GTX 1050 Ti · NVIDIA GTX 1650 Ti