NVIDIA Tesla P40
24 GB · 346 GB/s · 250 W
Prices
Every retailer we track in Germany, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What two of them run
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.8 GB | 256k | 7tok/sest. | 93 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 40.4 GB | 224k256k with q8 cache | 35tok/sest. | 246 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 7tok/sest. | 93 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | fits | 46.6 GB | 14k23k with q8 cache | 49tok/sest. | 621 tok/s | chat, coding |
| Gemma 4 31B | Q8_0 | fits | 32.9 GB | 172k256k with q8 cache | 6tok/sest. | 81 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 38.8 GB | 296k471k with q8 cache | 50tok/sest. | 321 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 39tok/sest. | 796 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 7tok/sest. | 93 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.5 GB | 256k | 28tok/sest. | 607 tok/s | chat, coding, long documents |
| GLM 4.5 Air Z.ai | Q2_K | fits | 44.8 GB | 18k34k with q8 cache | 15tok/sest. | 123 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | fits | 46.6 GB | 15k24k with q8 cache | 62tok/sest. | 780 tok/s | chat, coding, agents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 39tok/sest. | 796 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 31.2 GB | 198k | 23tok/sest. | 445 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 137k251k with q8 cache | 8tok/sest. | 105 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.8 GB | 256k | 38tok/sest. | 829 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 38.9 GB | 588k802k with q8 cache | 50tok/sest. | 757 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 128k | 49tok/sest. | 576 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 32.1 GB | 155k256k with q8 cache | 32tok/sest. | 576 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.6 GB | 40k | 6tok/sest. | 72 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 16tok/sest. | 211 tok/s | chat |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 22tok/sest. | 268 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 8tok/sest. | 105 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 28.9 GB | 128k | 7tok/sest. | 94 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.6 GB | 51k95k with q8 cache | 6tok/sest. | 75 tok/s | – |
| Llama 3.3 70B Meta | Q4_K_M | fits | 43.2 GB | 19k35k with q8 cache | 5tok/sest. | 35 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.8 GB | 199k256k with q8 cache | 14tok/sest. | 174 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.0 GB | 40k | 13tok/sest. | 161 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 128k | 22tok/sest. | 283 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 40k | 22tok/sest. | 283 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.2 GB | 16k | 12tok/sest. | 163 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 256k | 45tok/sest. | 539 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 256k | 21tok/sest. | 264 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 128k | 20tok/sest. | 262 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 25tok/sest. | 324 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 125k | 88tok/sest. | 1893 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 128k | 28tok/sest. | 292 tok/s | chat |
| gpt-oss 120B OpenAI | MXFP4 | offload | 60.5 GB | – | 22tok/sest. | 359 tok/s | chat |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.3 GB | – | 18tok/sest. | 203 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 92.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.6 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.9 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 73.2 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Tesla P40
- Memory
- 24 GB GDDR5
- Memory bus
- 384-bit
- Memory bandwidth
- 346 GB/s
- FP16 compute
- 11.8 TFLOPS
- Software
- CUDA
- Board power
- 250 W
- PCIe generation
- Gen 3
- PCIe lanes
- x16