NVIDIA Tesla P40
24 GB · 346 GB/s · 250 W
Prices
Every retailer we track in the US, 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 @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.5 GB | 256k | 7tok/sest. | 86 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 41.1 GB | 224k256k with q8 cache | 30tok/sest. | 201 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 30.1 GB | 256k | 7tok/sest. | 86 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 35.0 GB | 172k256k with q8 cache | 6tok/sest. | 76 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 39.4 GB | 296k471k with q8 cache | 41tok/sest. | 223 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 34tok/sest. | 611 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 30.1 GB | 256k | 7tok/sest. | 86 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.1 GB | 256k | 26tok/sest. | 544 tok/s | chat, coding, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 34tok/sest. | 611 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 32.6 GB | 198k | 18tok/sest. | 319 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.6 GB | 137k251k with q8 cache | 7tok/sest. | 90 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.1 GB | 256k | 36tok/sest. | 698 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 39.3 GB | 588k802k with q8 cache | 46tok/sest. | 527 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.3 GB | 128k | 40tok/sest. | 457 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 34.5 GB | 155k256k with q8 cache | 20tok/sest. | 281 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 41.7 GB | 40k | 5tok/sest. | 53 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.9 GB | 256k | 16tok/sest. | 199 tok/s | chat |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 11.2 GB | 256k | 20tok/sest. | 248 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 29.6 GB | 128k | 7tok/sest. | 90 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 30.9 GB | 128k | 7tok/sest. | 91 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 41.7 GB | 51k95k with q8 cache | 5tok/sest. | 61 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.7 GB | 199k256k with q8 cache | 11tok/sest. | 138 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.9 GB | 40k | 10tok/sest. | 124 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.9 GB | 128k | 16tok/sest. | 204 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.9 GB | 40k | 16tok/sest. | 204 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 22.0 GB | 16k | 10tok/sest. | 124 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.5 GB | 256k | 38tok/sest. | 463 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.9 GB | 256k | 16tok/sest. | 197 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 15.0 GB | 128k | 15tok/sest. | 188 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 9.8 GB | 128k | 23tok/sest. | 311 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 11.2 GB | 125k | 48tok/sest. | 1017 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 11.4 GB | 128k | 20tok/sest. | 215 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.3 GB | 14k23k with q8 cache | 39tok/sest. | 481 tok/s | chat, coding |
| gpt-oss 120B OpenAI | MXFP4 | offload | 61.5 GB | – | 17tok/sest. | 277 tok/s | chat |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.6 GB | – | 17tok/sest. | 189 tok/s | chat |
| GLM 4.5 Air Z.ai | Q2_K | offload | 49.2 GB | 18k34k with q8 cache | 9tok/sest. | 72 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.3 GB | 15k24k with q8 cache | 47tok/sest. | 572 tok/s | chat, coding, agents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 50.9 GB | 19k35k with q8 cache | 3tok/sest. | 27 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 94.2 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.0 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.6 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 79.2 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