readygpu

NVIDIA RTX 6000 Ada Generation vs NVIDIA Tesla P40

For running models locally, priced in the UK. At 128k context the first runs 60 models fully in memory, the second 31.

In short

The NVIDIA RTX 6000 Ada Generation has more memory for models: 48 GB against 24 GB. At 128k context the NVIDIA RTX 6000 Ada Generation runs 60 of the models we track fully in memory and the NVIDIA Tesla P40 31; only the NVIDIA RTX 6000 Ada Generation holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA RTX 6000 Ada Generation is about 2.8× as fast as the NVIDIA Tesla P40 (estimated, median across models).

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

NVIDIA RTX 6000 Ada Generation

Not priced here

Add to build
NVIDIA Tesla P40

£234

eBay

Add to build

Specifications

SpecNVIDIA RTX 6000 Ada GenerationNVIDIA Tesla P40
GPURTX 6000 Ada GenerationTesla P40
Memory48 GB GDDR624 GB GDDR5
Memory bus384-bit384-bit
Memory bandwidth960 GB/s346 GB/s
FP16 compute91.1 TFLOPS11.8 TFLOPS
SoftwareCUDACUDA
Board power300 W250 W
PCIe generationGen 4Gen 3
PCIe lanesx16x16

What each runs

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

ModelNVIDIA RTX 6000 Ada GenerationNVIDIA Tesla P40
Qwen 3.8 27B16tok/sQ8_0offload
Qwen 3.5 122B-A10B53tok/sUD-Q2_K_XLoffload
Qwen 3.6 27B16tok/sQ8_0offload
Gemma 4 31B14tok/sQ8_0offload
Mistral Small 4 119B66tok/sUD-Q2_K_XLoffload
Qwen 3.6 35B-A3B61tok/sQ8_0offload
Qwen 3.5 27B16tok/sQ8_0offload
Gemma 4 26B-A4B51tok/sQ8_022tok/sQ5_K_M
Qwen 3.5 35B-A3B61tok/sQ8_0offload
GLM 4.7 Flash29tok/sQ8_0offload
Devstral Small 2 24B13tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B86tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B100tok/sQ6_Koffload
gpt-oss 20B63tok/sMXFP423tok/sMXFP4
Qwen3 Coder 30B-A3B22tok/sQ8_0offload
Gemma 4 12B39tok/sQ8_014tok/sQ8_0
Qwen 3.5 9B43tok/sQ8_016tok/sQ8_0
Gemma 3 27B15tok/sQ8_0offload
Mistral Small 3.2 24B13tok/sQ8_0offload
Ministral 3 14B17tok/sQ8_0offload
Qwen3 14B16tok/sQ8_0offload
DeepSeek R1 0528 Qwen3 8B21tok/sQ8_0offload
Qwen3 8B21tok/sQ8_0offload
Phi-4 14B14tok/sQ8_0offload
Qwen 3.5 4B67tok/sQ8_024tok/sQ8_0
Ministral 3 8B22tok/sQ8_09tok/sQ4_K_M
Granite 4.2 8B19tok/sQ8_0offload
Gemma 4 E4B50tok/sQ8_018tok/sQ8_0
LFM2.5 8B-A1B48tok/sQ8_017tok/sQ8_0
Llama 3.1 8B25tok/sQ6_K9tok/sQ5_K_M
Qwen2.5 0.5B278tok/sQ8_0100tok/sQ8_0
Qwen3.5 0.8B244tok/sQ8_088tok/sQ8_0
Qwen3.5 2B194tok/sQ5_K_M70tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B105tok/sQ8_038tok/sQ8_0
Mellum2.1 12B A2.5B Thinking78tok/sQ8_028tok/sQ8_0
Spark X2.5 4B75tok/smlx-4bit27tok/smlx-4bit
MiniCPM5 2B72tok/sQ8_026tok/sQ8_0
FrogNano 4B 260966tok/sQ8_024tok/sQ8_0
LFM2.5 2.6B55tok/sQ8_020tok/sQ8_0
LFM2.5 VL 3B55tok/sQ8_020tok/sQ8_0
Kimi VL A3B Thinking 250650tok/sQ8_018tok/sQ8_0
Kimi VL A3B49tok/smlx-8bit18tok/smlx-8bit
GLM 4 9B 041444tok/smlx-5bit16tok/smlx-5bit
granite vision 4.1 4b42tok/sQ8_015tok/sQ8_0
granite 4.2 3b41tok/sQ8_015tok/sQ8_0
GLM 4.6V Flash39tok/sQ8_014tok/sQ8_0
DeepSeek R1 Distill Qwen 7B38tok/sQ8_014tok/sQ8_0
GLM 4.1V 9B Thinking35tok/smlx-8bit13tok/smlx-8bit
Ministral 3 3B Instruct 251234tok/sQ8_012tok/sQ8_0
LFM2.5 24B A2B28tok/sQ8_0offload
DeepSeek R1 Distill Llama 8B23tok/sQ8_09tok/sQ5_K_M
Ministral 3 8B Reasoning 251222tok/sQ8_09tok/sQ4_K_M
Qwen3.8 27B OBLITERATED20tok/smlx-4bitoffload
Muse Glimmer 30B17tok/sQ8_010tok/sQ5_K_M
Ministral 3 14B Reasoning 251217tok/sQ8_0offload
DeepSeek R1 Distill Qwen 14B14tok/sQ8_0offload
Devstral Small 250713tok/sQ8_0offload
Magistral Small 250613tok/sQ8_0offload
Magistral Small 250713tok/sQ8_0offload
Magistral Small 250913tok/sQ8_0offload
Qwen3 Coder Nextoffloadwon't run
Nemotron 3 Super 120B-A12Boffloadwon't run
gpt-oss 120Boffloadwon't run
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Qwen3 32Boffloadwon't run
DeepSeek R1 Distill Qwen 32Boffloadwon't run
granite 4.2 30boffloadwon't run
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
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 RTX 6000 Ada Generation or the NVIDIA Tesla P40?
Choose the NVIDIA RTX 6000 Ada Generation to run bigger models. Choose the NVIDIA RTX 6000 Ada Generation for speed.
Which can run bigger models, the NVIDIA RTX 6000 Ada Generation or the NVIDIA Tesla P40?
At 128k context the NVIDIA RTX 6000 Ada Generation runs 60 of the models we track fully in memory and the NVIDIA Tesla P40 31; only the NVIDIA RTX 6000 Ada Generation holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA RTX 6000 Ada Generation or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA RTX 6000 Ada Generation is about 2.8× as fast as the NVIDIA Tesla P40 (estimated, median across models).

More comparisons

More hardware for local AI