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 it runs
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 | UD-Q5_K_M | fits | 21.4 GB | 60k106k with q8 cache | 10tok/sest. | 86 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q5_K_M | fits | 21.2 GB | 64k112k with q8 cache | 10tok/sest. | 86 tok/s | – |
| Gemma 4 31B | Q4_K_M | fits | 21.2 GB | 57k110k with q8 cache | 10tok/sest. | 76 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | fits | 22.2 GB | 79k124k with q8 cache | 50tok/sest. | 611 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q5_K_M | fits | 21.3 GB | 62k110k with q8 cache | 10tok/sest. | 86 tok/s | – |
| Gemma 4 26B-A4B | UD-Q6_K | fits | 23.3 GB | 36k62k with q8 cache | 29tok/sest. | 544 tok/s | chat, coding, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | fits | 22.1 GB | 84k131k with q8 cache | 50tok/sest. | 611 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q5_K_M | fits | 22.5 GB | 48k82k with q8 cache | 24tok/sest. | 319 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q5_K_M | fits | 21.5 GB | 43k79k with q8 cache | 10tok/sest. | 90 tok/s | – |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.9 GB | 128k | 40tok/sest. | 457 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | fits | 21.2 GB | 54k97k with q8 cache | 26tok/sest. | 281 tok/s | chat, coding |
| Gemma 4 12B | Q8_0 | fits | 13.5 GB | 256k | 16tok/sest. | 199 tok/s | chat |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.8 GB | 256k | 20tok/sest. | 248 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q5_K_M | fits | 21.5 GB | 43k79k with q8 cache | 10tok/sest. | 90 tok/s | – |
| Gemma 3 27B | Q5_K_M | fits | 21.7 GB | 51k95k with q8 cache | 10tok/sest. | 91 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.3 GB | 57k104k with q8 cache | 11tok/sest. | 138 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.5 GB | 40k | 10tok/sest. | 124 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.5 GB | 99k128k with q8 cache | 16tok/sest. | 204 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.5 GB | 40k | 16tok/sest. | 204 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 21.6 GB | 16k | 10tok/sest. | 124 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.1 GB | 256k | 38tok/sest. | 463 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.5 GB | 103k187k with q8 cache | 16tok/sest. | 197 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.6 GB | 86k128k with q8 cache | 15tok/sest. | 188 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 9.4 GB | 128k | 23tok/sest. | 311 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.8 GB | 125k | 48tok/sest. | 1017 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 11.0 GB | 126k128k with q8 cache | 20tok/sest. | 215 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.7 GB | – | 13tok/sest. | 148 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.9 GB | – | 16tok/sest. | 336 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.0 GB | – | 19tok/sest. | 168 tok/s | chat |
| GLM 4.5 Air Z.ai | Q2_K | offload | 48.8 GB | – | 4tok/sest. | 51 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.9 GB | – | 19tok/sest. | 399 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.7 GB | – | 19tok/sest. | 566 tok/s | chat, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.2 GB | – | 37tok/sest. | 463 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 27.3 GB | 16k30k with q8 cache | 5tok/sest. | 49 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 27.4 GB | 16k30k with q8 cache | 5tok/sest. | 56 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.8 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 | 75.2 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.8 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.2 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 61.1 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.5 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