NVIDIA Tesla P40 vs NVIDIA GeForce RTX 5070 Ti
For running models locally, priced in the US. At 64k context the first runs 22 models fully in memory, the second 10.
Specifications
| Spec | NVIDIA Tesla P40 | NVIDIA GeForce RTX 5070 Ti |
|---|---|---|
| GPU | Tesla P40 | GeForce RTX 5070 Ti |
| Memory | 24 GB GDDR5 | 16 GB GDDR7 |
| Memory bus | 384-bit | 256-bit |
| Memory bandwidth | 346 GB/s | 896 GB/s |
| FP16 compute | 11.8 TFLOPS | 88 TFLOPS |
| Software | CUDA | CUDA |
| Board power | 250 W | 300 W |
| PCIe generation | Gen 3 | Gen 5 |
| PCIe lanes | x16 | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | NVIDIA Tesla P40 | NVIDIA GeForce RTX 5070 Ti |
|---|---|---|
| Qwen 3.8 27B | 10tok/sUD-Q4_K_M | offload |
| Qwen 3.6 27B | 9tok/sQ5_K_M | offload |
| Qwen 3.6 35B-A3B | 40tok/sUD-Q4_K_M | offload |
| Qwen 3.5 27B | 10tok/sQ4_K_M | offload |
| Gemma 4 26B-A4B | 27tok/sUD-Q5_K_M | offload |
| Qwen 3.5 35B-A3B | 40tok/sQ4_K_M | offload |
| GLM 4.7 Flash | 20tok/sQ4_K_M | offload |
| gpt-oss 20B | 32tok/sMXFP4 | 83tok/sMXFP4 |
| Gemma 4 12B | 15tok/sQ8_0 | 40tok/sQ8_0 |
| Qwen 3.5 9B | 18tok/sQ8_0 | 47tok/sQ8_0 |
| Gemma 3 27B | 10tok/sQ4_K_M | offload |
| Ministral 3 14B | 10tok/sQ6_K | offload |
| Qwen3 14B | 9tok/sQ6_K | offload |
| DeepSeek R1 0528 Qwen3 8B | 12tok/sQ8_0 | 38tok/sQ4_K_M |
| Qwen3 8B | 12tok/sQ8_0 | 38tok/sQ4_K_M |
| Phi-4 14B | 9tok/sQ5_K_M | offload |
| Qwen 3.5 4B | 32tok/sQ8_0 | 83tok/sQ8_0 |
| Ministral 3 8B | 12tok/sQ8_0 | 37tok/sQ5_K_M |
| Granite 4.2 8B | 11tok/sQ8_0 | offload |
| Gemma 4 E4B | 21tok/sQ8_0 | 55tok/sQ8_0 |
| LFM2.5 8B-A1B | 30tok/sQ8_0 | 78tok/sQ8_0 |
| Llama 3.1 8B | 14tok/sQ6_K | 37tok/sQ6_K |
| Qwen 3.5 122B-A10B | offload | won't run |
| Qwen3 Coder Next | offload | won't run |
| Gemma 4 31B | offload | offload |
| Mistral Small 4 119B | offload | offload |
| Qwen3 Next 80B-A3B | offload | won't run |
| Devstral Small 2 24B | offload | offload |
| Nemotron 3.5 Lightning 30B-A3B | offload | offload |
| Kimi Linear 48B-A3B | offload | offload |
| Qwen3 Coder 30B-A3B | offload | offload |
| Qwen3 32B | offload | offload |
| Mistral Small 3.2 24B | offload | offload |
| DeepSeek R1 Distill Qwen 32B | offload | offload |
| DeepSeek V4 Flash | won't run | won't run |
| GLM 5.3 Flash | won't run | won't run |
| Qwen 3.8 Flash Next | won't run | won't run |
| MiniMax M2.7 | won't run | won't run |
| Nemotron 3 Super 120B-A12B | won't run | won't run |
| gpt-oss 120B | won't run | won't run |
| GLM 4.5 Air | won't run | won't run |
| Llama 3.3 70B | won't run | won't run |