readygpu

NVIDIA GeForce RTX 5050 vs NVIDIA Tesla P40

For running models locally, priced in Germany. At 32k context the first runs 18 models fully in memory, the second 58.

In short

The NVIDIA Tesla P40 has more memory for models: 24 GB against 8 GB. At 32k context the NVIDIA Tesla P40 runs 58 of the models we track fully in memory and the NVIDIA GeForce RTX 5050 18; only the NVIDIA Tesla P40 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA Tesla P40 is about 1.1× as fast as the NVIDIA GeForce RTX 5050 (estimated, median across models). In Germany the NVIDIA GeForce RTX 5050 costs 387 € at eBay and the NVIDIA Tesla P40 369 € at eBay (used): the NVIDIA Tesla P40 is 18 € cheaper.

Updated . Speeds are estimates; how they are worked out.

NVIDIA GeForce RTX 5050

387 €

eBay

Add to build
NVIDIA Tesla P40

369 €

eBay, used (asking)

Add to build

Specifications

SpecNVIDIA GeForce RTX 5050NVIDIA Tesla P40
GPUGeForce RTX 5050Tesla P40
Memory8 GB GDDR624 GB GDDR5
Memory bus128-bit384-bit
Memory bandwidth320 GB/s346 GB/s
FP16 compute13.169 TFLOPS11.8 TFLOPS
SoftwareCUDACUDA
Board power130 W250 W
PCIe generationGen 5Gen 3
PCIe lanesx8x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelNVIDIA GeForce RTX 5050NVIDIA Tesla P40
Qwen 3.8 27Boffload9tok/sQ5_K_M
Qwen 3.6 27Boffload10tok/sQ5_K_M
Gemma 4 31Boffload10tok/sQ4_K_M
Qwen 3.6 35B-A3Boffload50tok/sQ4_K_M
Qwen 3.5 27Boffload10tok/sQ5_K_M
Gemma 4 26B-A4Boffload29tok/sUD-Q6_K
Qwen 3.5 35B-A3Boffload50tok/sQ4_K_M
GLM 4.7 Flashoffload24tok/sQ5_K_M
Devstral Small 2 24Boffload10tok/sQ5_K_M
Nemotron 3.5 Lightning 30B-A3Boffload52tok/sMXFP4
gpt-oss 20Boffload40tok/sMXFP4
Qwen3 Coder 30B-A3Boffload26tok/sQ4_K_M
Gemma 4 12Boffload16tok/sQ8_0
Qwen 3.5 9B29tok/sQ4_K_M20tok/sQ8_0
Gemma 3 27Boffload10tok/sQ5_K_M
Mistral Small 3.2 24Boffload10tok/sQ5_K_M
Ministral 3 14Boffload11tok/sQ8_0
Qwen3 14Boffload10tok/sQ8_0
DeepSeek R1 0528 Qwen3 8Boffload16tok/sQ8_0
Qwen3 8Boffload16tok/sQ8_0
Phi-4 14Boffload10tok/sQ8_0
Qwen 3.5 4B35tok/sQ8_038tok/sQ8_0
Ministral 3 8Boffload16tok/sQ8_0
Granite 4.2 8Boffload15tok/sQ8_0
Gemma 4 E4B31tok/sQ5_K_M23tok/sQ8_0
LFM2.5 8B-A1B53tok/sMXFP448tok/sQ8_0
Llama 3.1 8Boffload20tok/sQ6_K
Qwen2.5 0.5B213tok/sQ8_0230tok/sQ8_0
Qwen3.5 0.8B161tok/sQ8_0174tok/sQ8_0
Qwen3.5 2B107tok/sQ5_K_M116tok/sQ5_K_M
LFM3 1.7B88tok/sQ8_095tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B70tok/sQ8_076tok/sQ8_0
MiniCPM5 2B49tok/sQ8_053tok/sQ8_0
Spark X2.5 4B46tok/smlx-4bit50tok/smlx-4bit
LFM2.5 2.6B41tok/sQ8_044tok/sQ8_0
LFM2.5 VL 3B41tok/sQ8_044tok/sQ8_0
FrogNano 4B 260935tok/sQ8_037tok/sQ8_0
granite vision 4.1 4b32tok/sQ8_034tok/sQ8_0
Ministral 3 3B Instruct 251231tok/sQ6_K30tok/sQ8_0
DeepSeek R1 Distill Qwen 7B30tok/sQ4_K_M22tok/sQ8_0
granite 4.2 3b30tok/sQ8_033tok/sQ8_0
Mellum2.1 12B A2.5B Thinkingoffload41tok/sQ8_0
GLM 4.6V Flashoffload19tok/sQ8_0
Kimi VL A3B Thinking 2506offload31tok/sQ8_0
Kimi VL A3Boffload30tok/smlx-8bit
GLM 4 9B 0414offload22tok/smlx-5bit
DeepSeek R1 Distill Llama 8Boffload17tok/sQ8_0
Ministral 3 8B Reasoning 2512offload16tok/sQ8_0
LFM2.5 24B A2Boffload29tok/sQ6_K
GLM 4.1V 9B Thinkingoffload16tok/smlx-8bit
Ministral 3 14B Reasoning 2512offload11tok/sQ8_0
DeepSeek R1 Distill Qwen 14Boffload10tok/sQ8_0
Muse Glimmer 30Boffload9tok/sQ6_K
Devstral Small 2507offload10tok/sQ5_K_M
Magistral Small 2506offload10tok/sQ5_K_M
Magistral Small 2507offload10tok/sQ5_K_M
Magistral Small 2509offload10tok/sQ5_K_M
Qwen3.8 27B OBLITERATEDoffload9tok/smlx-4bit
Qwen 3.5 122B-A10Bwon't runoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Bwon't runoffload
GLM 4.5 Airwon't runoffload
Qwen3 Next 80B-A3Bwon't runoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
granite 4.2 30boffloadoffload
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
Qwen 3.8 Flash Nextwon't runwon't run
MiniMax M2.7won't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
gpt-oss 120Bwon't runwon't run
Llama 3.3 70Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Distill Llama 70Bwon't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5won't runwon't run
GLM 4.5Vwon't runwon't run
GLM 4.6won't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won't runwon't run
GLM 5won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi Dev 72Bwon't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run
Mistral Medium 3.5 128Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 5050 or the NVIDIA Tesla P40?
Choose the NVIDIA Tesla P40 to run bigger models. Choose the NVIDIA Tesla P40 for speed. Choose the NVIDIA Tesla P40 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 5050 or the NVIDIA Tesla P40?
At 32k context the NVIDIA Tesla P40 runs 58 of the models we track fully in memory and the NVIDIA GeForce RTX 5050 18; only the NVIDIA Tesla P40 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 5050 or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA Tesla P40 is about 1.1× as fast as the NVIDIA GeForce RTX 5050 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 5050 and the NVIDIA Tesla P40?
In Germany the NVIDIA GeForce RTX 5050 costs 387 € at eBay and the NVIDIA Tesla P40 369 € at eBay (used): the NVIDIA Tesla P40 is 18 € cheaper.

More comparisons

More hardware for local AI