NVIDIA RTX 2080 Ti 22GB (modded) vs NVIDIA Tesla P40 24GB for local LLMs
7 reports on the NVIDIA RTX 2080 Ti 22GB (modded) and 8 on the NVIDIA Tesla P40 24GB
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 4-bit, the NVIDIA RTX 2080 Ti 22GB (modded) runs at 69.0 tokens per second (one run) and the NVIDIA Tesla P40 24GB at 9.7 (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 1.8x higher on the NVIDIA RTX 2080 Ti 22GB (modded) (616 GB/s on the NVIDIA RTX 2080 Ti 22GB (modded), 346 on the NVIDIA Tesla P40 24GB).
- Memory
- 22GB
- Memory bandwidth
- 616 GB/s
- FP16 compute
- 108 TFLOPS
- Reports
- 7
- Memory
- 24GB
- Memory bandwidth
- 346 GB/s
- FP16 compute
- 12 TFLOPS
- Reports
- 8
Measured on both
Median tokens per second from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same quant level. Engines and context lengths can still differ between the runs. How to read these
| Model | NVIDIA RTX 2080 Ti 22GB (modded) | NVIDIA Tesla P40 24GB |
|---|---|---|
| Qwen3.6 35B · 3B active4-bit | 69.0one run | 9.7one run |
Estimated by the calculator
The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape. Where a model was also measured above, the measurement wins.
| Model | NVIDIA RTX 2080 Ti 22GB (modded) | NVIDIA Tesla P40 24GB |
|---|---|---|
| Qwen3.6 35B · 3B active | 93.6 t/sQ3_K_M | 44.4 t/sQ4_K_S |
| Qwen3.8 27B | 25.1 t/sQ4_K_S | 12.5 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | 18.6 t/sQ2_K, experts in RAM | 16.9 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 25.1 t/sQ4_K_S | 12.5 t/sQ4_K_M |
| Gemma 4 26B · 4B active | 56.6 t/sQ4_K_M | 28.2 t/sQ5_K_S |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: NVIDIA RTX 2080 Ti 22GB (modded) · NVIDIA Tesla P40 24GB
Every report on each card, with its source: NVIDIA RTX 2080 Ti 22GB (modded) · NVIDIA Tesla P40 24GB