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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 32.7 GB | 256k | 6tok/sest. | 78 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 42.1 GB | 224k256k with q8 cache | 25tok/sest. | 162 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 32.2 GB | 256k | 7tok/sest. | 78 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 37.7 GB | 172k256k with q8 cache | 6tok/sest. | 71 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 40.3 GB | 296k471k with q8 cache | 33tok/sest. | 159 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 29tok/sest. | 467 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 32.2 GB | 256k | 7tok/sest. | 78 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.9 GB | 256k | 23tok/sest. | 478 tok/s | chat, coding, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 29tok/sest. | 467 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.4 GB | 198k | 15tok/sest. | 232 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 34.8 GB | 137k251k with q8 cache | 6tok/sest. | 76 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.5 GB | 256k | 34tok/sest. | 576 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 39.7 GB | 588k802k with q8 cache | 42tok/sest. | 375 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.3 GB | 128k | 32tok/sest. | 358 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.7 GB | 155k256k with q8 cache | 13tok/sest. | 167 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 42.5 GB | 40k | 5tok/sest. | 40 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 14.6 GB | 256k | 15tok/sest. | 184 tok/s | chat |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.4 GB | 256k | 18tok/sest. | 225 tok/s | chat, coding |
| Gemma 3 27B | Q8_0 | fits | 33.6 GB | 128k | 6tok/sest. | 87 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 34.8 GB | 128k | 6tok/sest. | 76 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 42.5 GB | 80k128k with q8 cache | 5tok/sest. | 49 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.8 GB | 199k256k with q8 cache | 9tok/sest. | 108 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.1 GB | 40k | 8tok/sest. | 94 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.6 GB | 128k | 12tok/sest. | 149 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.6 GB | 40k | 12tok/sest. | 149 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.5 GB | 16k | 7tok/sest. | 95 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.7 GB | 256k | 32tok/sest. | 390 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.4 GB | 256k | 12tok/sest. | 147 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.2 GB | 128k | 11tok/sest. | 136 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 10.9 GB | 128k | 21tok/sest. | 295 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.9 GB | 125k | 30tok/sest. | 629 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.6 GB | 128k | 14tok/sest. | 160 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.2 GB | 14k23k with q8 cache | 29tok/sest. | 367 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.0 GB | – | 16tok/sest. | 174 tok/s | chat |
| gpt-oss 120B OpenAI | MXFP4 | offload | 62.8 GB | – | 13tok/sest. | 211 tok/s | chat |
| GLM 4.5 Air Z.ai | Q2_K | offload | 55.2 GB | 18k34k with q8 cache | 5tok/sest. | 45 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.2 GB | 15k24k with q8 cache | 34tok/sest. | 419 tok/s | chat, coding, agents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 61.1 GB | 19k35k with q8 cache | 2tok/sest. | 20 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 97.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.5 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.5 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 87.1 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