readygpu

NVIDIA RTX 6000 Ada Generation vs NVIDIA Tesla P40

For running models locally, priced in Germany. At 8k context the first runs 68 models fully in memory, the second 60.

In short

The NVIDIA RTX 6000 Ada Generation has more memory for models: 48 GB against 24 GB. At 8k context the NVIDIA RTX 6000 Ada Generation runs 68 of the models we track fully in memory and the NVIDIA Tesla P40 60; only the NVIDIA RTX 6000 Ada Generation holds Qwen 3.5 122B-A10B. 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

369 €

eBay, used (asking)

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 27B20tok/sQ8_010tok/sUD-Q6_K
Qwen 3.5 122B-A10B97tok/sUD-Q2_K_XLoffload
Qwen 3.6 27B20tok/sQ8_09tok/sQ6_K
Qwen3 Coder Next135tok/sQ4_K_Moffload
Gemma 4 31B17tok/sQ8_09tok/sQ5_K_M
Mistral Small 4 119B139tok/sUD-Q2_K_XLoffload
Qwen 3.6 35B-A3B108tok/sQ8_062tok/sQ4_K_M
Qwen 3.5 27B20tok/sQ8_09tok/sQ6_K
Gemma 4 26B-A4B79tok/sQ8_032tok/sUD-Q6_K
GLM 4.5 Air49tok/sQ2_Koffload
Qwen3 Next 80B-A3B173tok/sQ4_K_Moffload
Qwen 3.5 35B-A3B108tok/sQ8_062tok/sQ4_K_M
GLM 4.7 Flash62tok/sQ8_032tok/sQ5_K_M
Devstral Small 2 24B23tok/sQ8_010tok/sQ6_K
Nemotron 3.5 Lightning 30B-A3B104tok/sUD-Q6_K_XL56tok/sMXFP4
Kimi Linear 48B-A3B139tok/sQ6_Koffload
gpt-oss 20B136tok/sMXFP449tok/sMXFP4
Qwen3 Coder 30B-A3B89tok/sQ8_044tok/sQ5_K_M
Qwen3 32B16tok/sQ8_010tok/sQ4_K_M
Gemma 4 12B45tok/sQ8_016tok/sQ8_0
Qwen 3.5 9B60tok/sQ8_022tok/sQ8_0
Mistral Small 3.2 24B23tok/sQ8_010tok/sQ6_K
Gemma 3 27B20tok/sQ8_09tok/sQ6_K
DeepSeek R1 Distill Qwen 32B16tok/sQ8_010tok/sQ4_K_M
Llama 3.3 70B13tok/sQ4_K_Moffload
Ministral 3 14B38tok/sQ8_014tok/sQ8_0
Qwen3 14B35tok/sQ8_013tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B60tok/sQ8_022tok/sQ8_0
Qwen3 8B60tok/sQ8_022tok/sQ8_0
Phi-4 14B35tok/sQ8_012tok/sQ8_0
Qwen 3.5 4B124tok/sQ8_045tok/sQ8_0
Ministral 3 8B59tok/sQ8_021tok/sQ8_0
Granite 4.2 8B56tok/sQ8_020tok/sQ8_0
Gemma 4 E4B70tok/sQ8_025tok/sQ8_0
LFM2.5 8B-A1B244tok/sQ8_088tok/sQ8_0
Llama 3.1 8B78tok/sQ6_K28tok/sQ6_K
Qwen2.5 0.5B942tok/sQ8_0340tok/sQ8_0
Qwen3.5 0.8B639tok/sQ8_0230tok/sQ8_0
Qwen3.5 2B383tok/sQ5_K_M138tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B280tok/sQ8_0101tok/sQ8_0
MiniCPM5 2B196tok/sQ8_071tok/sQ8_0
LFM2.5 2.6B176tok/sQ8_064tok/sQ8_0
LFM2.5 VL 3B176tok/sQ8_064tok/sQ8_0
Spark X2.5 4B175tok/smlx-4bit63tok/smlx-4bit
granite vision 4.1 4b139tok/sQ8_050tok/sQ8_0
Ministral 3 3B Instruct 2512132tok/sQ8_047tok/sQ8_0
granite 4.2 3b130tok/sQ8_047tok/sQ8_0
LFM2.5 24B A2B128tok/sQ8_053tok/sQ6_K
Mellum2.1 12B A2.5B Thinking127tok/sQ8_046tok/sQ8_0
FrogNano 4B 2609121tok/sQ8_043tok/sQ8_0
Kimi VL A3B Thinking 2506106tok/sQ8_038tok/sQ8_0
Kimi VL A3B102tok/smlx-8bit37tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B70tok/sQ8_025tok/sQ8_0
GLM 4 9B 041469tok/smlx-5bit25tok/smlx-5bit
DeepSeek R1 Distill Llama 8B62tok/sQ8_022tok/sQ8_0
Ministral 3 8B Reasoning 251259tok/sQ8_021tok/sQ8_0
GLM 4.6V Flash58tok/sQ8_021tok/sQ8_0
GLM 4.1V 9B Thinking49tok/smlx-8bit18tok/smlx-8bit
Ministral 3 14B Reasoning 251238tok/sQ8_014tok/sQ8_0
DeepSeek R1 Distill Qwen 14B34tok/sQ8_012tok/sQ8_0
Qwen3.8 27B OBLITERATED28tok/smlx-4bit10tok/smlx-4bit
Devstral Small 250723tok/sQ8_012tok/sQ5_K_M
Magistral Small 250623tok/sQ8_010tok/sQ6_K
Magistral Small 250723tok/sQ8_012tok/sQ5_K_M
Magistral Small 250923tok/sQ8_012tok/sQ5_K_M
Muse Glimmer 30B18tok/sQ8_09tok/sQ6_K
granite 4.2 30b18tok/sQ8_09tok/sQ5_K_M
DeepSeek R1 Distill Llama 70B13tok/sQ4_K_Moffload
MiniMax M2.7offloadwon't run
Nemotron 3 Super 120B-A12Boffloadwon't run
gpt-oss 120Boffloadwon't run
GLM 4.5Voffloadwon't run
GLM 4.6Voffloadwon't run
Kimi Dev 72Boffloadwon't run
Devstral 2 123B Instruct 2512offloadwon't run
Mistral Medium 3.5 128Boffloadwon'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
DeepSeek R1won't runwon't run
DeepSeek R1 0528won'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
GLM 4.5won't runwon't run
GLM 4.6won'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 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

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 8k context the NVIDIA RTX 6000 Ada Generation runs 68 of the models we track fully in memory and the NVIDIA Tesla P40 60; only the NVIDIA RTX 6000 Ada Generation holds Qwen 3.5 122B-A10B.
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