readygpu

NVIDIA RTX 6000 Ada Generation vs NVIDIA Tesla P40

For running models locally, priced in the US. At 32k context the first runs 65 models fully in memory, the second 57.

In short

The NVIDIA RTX 6000 Ada Generation has more memory for models: 48 GB against 24 GB. At 32k context the NVIDIA RTX 6000 Ada Generation runs 65 of the models we track fully in memory and the NVIDIA Tesla P40 57; 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

$345

Amazon

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 27B19tok/sQ8_09tok/sQ5_K_M
Qwen 3.5 122B-A10B83tok/sUD-Q2_K_XLoffload
Qwen 3.6 27B19tok/sQ8_010tok/sQ5_K_M
Qwen3 Coder Next110tok/sQ4_K_Moffload
Gemma 4 31B17tok/sQ8_010tok/sQ4_K_M
Mistral Small 4 119B114tok/sUD-Q2_K_XLoffload
Qwen 3.6 35B-A3B94tok/sQ8_050tok/sQ4_K_M
Qwen 3.5 27B19tok/sQ8_010tok/sQ5_K_M
Gemma 4 26B-A4B71tok/sQ8_029tok/sUD-Q6_K
Qwen3 Next 80B-A3B134tok/sQ4_K_Moffload
Qwen 3.5 35B-A3B94tok/sQ8_050tok/sQ4_K_M
GLM 4.7 Flash51tok/sQ8_024tok/sQ5_K_M
Devstral Small 2 24B20tok/sQ8_010tok/sQ5_K_M
Nemotron 3.5 Lightning 30B-A3B100tok/sUD-Q6_K_XL52tok/sMXFP4
Kimi Linear 48B-A3B129tok/sQ6_Koffload
gpt-oss 20B110tok/sMXFP440tok/sMXFP4
Qwen3 Coder 30B-A3B56tok/sQ8_026tok/sQ4_K_M
Qwen3 32B14tok/sQ8_0offload
Gemma 4 12B44tok/sQ8_016tok/sQ8_0
Qwen 3.5 9B56tok/sQ8_020tok/sQ8_0
Mistral Small 3.2 24B20tok/sQ8_010tok/sQ5_K_M
Gemma 3 27B19tok/sQ8_010tok/sQ5_K_M
DeepSeek R1 Distill Qwen 32B14tok/sQ8_0offload
Ministral 3 14B30tok/sQ8_011tok/sQ8_0
Qwen3 14B28tok/sQ8_010tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B44tok/sQ8_016tok/sQ8_0
Qwen3 8B44tok/sQ8_016tok/sQ8_0
Phi-4 14B27tok/sQ8_010tok/sQ8_0
Qwen 3.5 4B106tok/sQ8_038tok/sQ8_0
Ministral 3 8B44tok/sQ8_016tok/sQ8_0
Granite 4.2 8B41tok/sQ8_015tok/sQ8_0
Gemma 4 E4B65tok/sQ8_023tok/sQ8_0
LFM2.5 8B-A1B134tok/sQ8_048tok/sQ8_0
Llama 3.1 8B55tok/sQ6_K20tok/sQ6_K
Qwen2.5 0.5B637tok/sQ8_0230tok/sQ8_0
Qwen3.5 0.8B483tok/sQ8_0174tok/sQ8_0
Qwen3.5 2B321tok/sQ5_K_M116tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B210tok/sQ8_076tok/sQ8_0
MiniCPM5 2B146tok/sQ8_053tok/sQ8_0
Spark X2.5 4B138tok/smlx-4bit50tok/smlx-4bit
LFM2.5 2.6B122tok/sQ8_044tok/sQ8_0
LFM2.5 VL 3B122tok/sQ8_044tok/sQ8_0
Mellum2.1 12B A2.5B Thinking113tok/sQ8_041tok/sQ8_0
FrogNano 4B 2609104tok/sQ8_037tok/sQ8_0
granite vision 4.1 4b94tok/sQ8_034tok/sQ8_0
granite 4.2 3b91tok/sQ8_033tok/sQ8_0
Kimi VL A3B Thinking 250687tok/sQ8_031tok/sQ8_0
Kimi VL A3B84tok/smlx-8bit30tok/smlx-8bit
Ministral 3 3B Instruct 251283tok/sQ8_030tok/sQ8_0
LFM2.5 24B A2B74tok/sQ8_029tok/sQ6_K
GLM 4 9B 041462tok/smlx-5bit22tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B60tok/sQ8_022tok/sQ8_0
GLM 4.6V Flash53tok/sQ8_019tok/sQ8_0
DeepSeek R1 Distill Llama 8B46tok/sQ8_017tok/sQ8_0
GLM 4.1V 9B Thinking45tok/smlx-8bit16tok/smlx-8bit
Ministral 3 8B Reasoning 251244tok/sQ8_016tok/sQ8_0
Ministral 3 14B Reasoning 251230tok/sQ8_011tok/sQ8_0
DeepSeek R1 Distill Qwen 14B27tok/sQ8_010tok/sQ8_0
Qwen3.8 27B OBLITERATED26tok/smlx-4bit9tok/smlx-4bit
Devstral Small 250720tok/sQ8_010tok/sQ5_K_M
Magistral Small 250620tok/sQ8_010tok/sQ5_K_M
Magistral Small 250720tok/sQ8_010tok/sQ5_K_M
Magistral Small 250920tok/sQ8_010tok/sQ5_K_M
Muse Glimmer 30B18tok/sQ8_09tok/sQ6_K
granite 4.2 30b15tok/sQ8_0offload
Nemotron 3 Super 120B-A12Boffloadwon't run
gpt-oss 120Boffloadwon't run
GLM 4.5 Airoffloadoffload
Llama 3.3 70Boffloadwon't run
DeepSeek R1 Distill Llama 70Boffloadwon't run
GLM 4.5Voffloadwon't run
GLM 4.6Voffloadwon't run
Kimi Dev 72Boffloadwon'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
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
Devstral 2 123B Instruct 2512won'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
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 32k context the NVIDIA RTX 6000 Ada Generation runs 65 of the models we track fully in memory and the NVIDIA Tesla P40 57; 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