readygpu

NVIDIA RTX 6000 Ada Generation vs NVIDIA Tesla P40

For running models locally, priced in the UK. At 64k context the first runs 63 models fully in memory, the second 48.

In short

The NVIDIA RTX 6000 Ada Generation has more memory for models: 48 GB against 24 GB. At 64k context the NVIDIA RTX 6000 Ada Generation runs 63 of the models we track fully in memory and the NVIDIA Tesla P40 48; 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

£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 27B18tok/sQ8_010tok/sQ4_K_M
Qwen 3.5 122B-A10B70tok/sUD-Q2_K_XLoffload
Qwen 3.6 27B18tok/sQ8_09tok/sQ5_K_M
Gemma 4 31B15tok/sQ8_0offload
Mistral Small 4 119B92tok/sUD-Q2_K_XLoffload
Qwen 3.6 35B-A3B80tok/sQ8_039tok/sQ4_K_M
Qwen 3.5 27B18tok/sQ8_010tok/sQ4_K_M
Gemma 4 26B-A4B63tok/sQ8_027tok/sUD-Q5_K_M
Qwen 3.5 35B-A3B80tok/sQ8_040tok/sQ4_K_M
GLM 4.7 Flash41tok/sQ8_020tok/sQ4_K_M
Devstral Small 2 24B17tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B95tok/sUD-Q6_K_XL49tok/sMXFP4
Kimi Linear 48B-A3B117tok/sQ6_Koffload
gpt-oss 20B88tok/sMXFP432tok/sMXFP4
Qwen3 Coder 30B-A3B37tok/sQ8_0offload
Qwen3 32B14tok/sQ6_Koffload
Gemma 4 12B42tok/sQ8_015tok/sQ8_0
Qwen 3.5 9B51tok/sQ8_018tok/sQ8_0
Gemma 3 27B17tok/sQ8_010tok/sQ4_K_M
Mistral Small 3.2 24B17tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B14tok/sQ6_Koffload
Ministral 3 14B24tok/sQ8_010tok/sQ6_K
Qwen3 14B23tok/sQ8_09tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B32tok/sQ8_012tok/sQ8_0
Qwen3 8B32tok/sQ8_012tok/sQ8_0
Phi-4 14B21tok/sQ8_09tok/sQ5_K_M
Qwen 3.5 4B89tok/sQ8_032tok/sQ8_0
Ministral 3 8B33tok/sQ8_012tok/sQ8_0
Granite 4.2 8B30tok/sQ8_011tok/sQ8_0
Gemma 4 E4B59tok/sQ8_021tok/sQ8_0
LFM2.5 8B-A1B83tok/sQ8_030tok/sQ8_0
Llama 3.1 8B39tok/sQ6_K14tok/sQ6_K
Qwen2.5 0.5B445tok/sQ8_0161tok/sQ8_0
Qwen3.5 0.8B364tok/sQ8_0131tok/sQ8_0
Qwen3.5 2B263tok/sQ5_K_M95tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B158tok/sQ8_057tok/sQ8_0
MiniCPM5 2B108tok/sQ8_039tok/sQ8_0
Spark X2.5 4B108tok/smlx-4bit39tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking98tok/sQ8_035tok/sQ8_0
FrogNano 4B 260987tok/sQ8_032tok/sQ8_0
LFM2.5 2.6B86tok/sQ8_031tok/sQ8_0
LFM2.5 VL 3B86tok/sQ8_031tok/sQ8_0
Kimi VL A3B Thinking 250669tok/sQ8_025tok/sQ8_0
Kimi VL A3B67tok/smlx-8bit24tok/smlx-8bit
granite vision 4.1 4b66tok/sQ8_024tok/sQ8_0
granite 4.2 3b64tok/sQ8_023tok/sQ8_0
Ministral 3 3B Instruct 251256tok/sQ8_020tok/sQ8_0
GLM 4 9B 041454tok/smlx-5bit20tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B50tok/sQ8_018tok/sQ8_0
LFM2.5 24B A2B48tok/sQ8_019tok/sQ5_K_M
GLM 4.6V Flash47tok/sQ8_017tok/sQ8_0
GLM 4.1V 9B Thinking41tok/smlx-8bit15tok/smlx-8bit
DeepSeek R1 Distill Llama 8B35tok/sQ8_013tok/sQ8_0
Ministral 3 8B Reasoning 251233tok/sQ8_012tok/sQ8_0
Ministral 3 14B Reasoning 251224tok/sQ8_010tok/sQ6_K
Qwen3.8 27B OBLITERATED24tok/smlx-4bitoffload
DeepSeek R1 Distill Qwen 14B21tok/sQ8_09tok/sQ5_K_M
Muse Glimmer 30B18tok/sQ8_010tok/sQ5_K_M
Devstral Small 250717tok/sQ8_0offload
Magistral Small 250617tok/sQ8_0offload
Magistral Small 250717tok/sQ8_0offload
Magistral Small 250917tok/sQ8_0offload
granite 4.2 30b12tok/sQ8_0offload
Qwen3 Coder Nextoffloadoffload
Nemotron 3 Super 120B-A12Boffloadwon't run
gpt-oss 120Boffloadwon't run
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadoffload
Llama 3.3 70Boffloadwon't run
GLM 4.5Voffloadwon't run
DeepSeek R1 Distill Llama 70Boffloadwon'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 4.6Vwon'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 64k context the NVIDIA RTX 6000 Ada Generation runs 63 of the models we track fully in memory and the NVIDIA Tesla P40 48; 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