readygpu

AMD Radeon RX 7600 XT vs NVIDIA Tesla P40

For running models locally, priced in the US. At 64k context the first runs 30 models fully in memory, the second 45.

In short

The NVIDIA Tesla P40 has more memory for models: 24 GB against 16 GB. At 64k context the NVIDIA Tesla P40 runs 45 of the models we track fully in memory and the AMD Radeon RX 7600 XT 30; only the NVIDIA Tesla P40 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA Tesla P40 is about 1.4× as fast as the AMD Radeon RX 7600 XT (estimated, median across models). In the US the AMD Radeon RX 7600 XT costs $410 at eBay (used) and the NVIDIA Tesla P40 $405 at eBay: the NVIDIA Tesla P40 is $5 cheaper.

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

AMD Radeon RX 7600 XT

$410

eBay, used (asking)

Add to build
NVIDIA Tesla P40

$405

eBay

Add to build

Specifications

SpecAMD Radeon RX 7600 XTNVIDIA Tesla P40
GPURadeon RX 7600 XTTesla P40
Memory16 GB GDDR624 GB GDDR5
Memory bus128-bit384-bit
Memory bandwidth288 GB/s346 GB/s
FP16 compute45 TFLOPS11.8 TFLOPS
SoftwareROCmCUDA
Board power190 W250 W
PCIe generationGen 4Gen 3
PCIe lanesx8x16

What each runs

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

ModelAMD Radeon RX 7600 XTNVIDIA Tesla P40
Qwen 3.8 27Boffload10tok/sQ4_K_M
Qwen 3.6 27Boffload9tok/sQ5_K_M
Qwen 3.6 35B-A3Boffload39tok/sQ4_K_M
Qwen 3.5 27Boffload10tok/sQ4_K_M
Gemma 4 26B-A4Boffload27tok/sUD-Q5_K_M
Qwen 3.5 35B-A3Boffload40tok/sQ4_K_M
GLM 4.7 Flashoffload20tok/sQ4_K_M
Nemotron 3.5 Lightning 30B-A3Boffload49tok/sMXFP4
gpt-oss 20B24tok/sMXFP432tok/sMXFP4
Gemma 4 12B11tok/sQ8_015tok/sQ8_0
Qwen 3.5 9B14tok/sQ8_018tok/sQ8_0
Gemma 3 27Boffload10tok/sQ4_K_M
Ministral 3 14Boffload10tok/sQ6_K
Qwen3 14Boffload9tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B11tok/sQ4_K_M12tok/sQ8_0
Qwen3 8B11tok/sQ4_K_M12tok/sQ8_0
Phi-4 14Boffload9tok/sQ5_K_M
Qwen 3.5 4B24tok/sQ8_032tok/sQ8_0
Ministral 3 8B11tok/sQ4_K_M12tok/sQ8_0
Granite 4.2 8Boffload11tok/sQ8_0
Gemma 4 E4B16tok/sQ8_021tok/sQ8_0
LFM2.5 8B-A1B22tok/sQ8_030tok/sQ8_0
Llama 3.1 8B11tok/sQ5_K_M14tok/sQ6_K
Qwen2.5 0.5B119tok/sQ8_0161tok/sQ8_0
Qwen3.5 0.8B97tok/sQ8_0131tok/sQ8_0
Qwen3.5 2B70tok/sQ5_K_M95tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B42tok/sQ8_057tok/sQ8_0
MiniCPM5 2B29tok/sQ8_039tok/sQ8_0
Spark X2.5 4B29tok/smlx-4bit39tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking26tok/sQ8_035tok/sQ8_0
Kimi VL A3B Thinking 250624tok/sQ4_K_M25tok/sQ8_0
FrogNano 4B 260923tok/sQ8_032tok/sQ8_0
LFM2.5 2.6B23tok/sQ8_031tok/sQ8_0
LFM2.5 VL 3B23tok/sQ8_031tok/sQ8_0
Kimi VL A3B23tok/smlx-5bit24tok/smlx-8bit
granite vision 4.1 4b18tok/sQ8_024tok/sQ8_0
granite 4.2 3b17tok/sQ8_023tok/sQ8_0
GLM 4 9B 041415tok/smlx-5bit20tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B13tok/sQ8_018tok/sQ8_0
GLM 4.6V Flash13tok/sQ8_017tok/sQ8_0
DeepSeek R1 Distill Llama 8B11tok/sQ5_K_M13tok/sQ8_0
Ministral 3 8B Reasoning 251211tok/sQ4_K_M12tok/sQ8_0
GLM 4.1V 9B Thinking11tok/smlx-8bit15tok/smlx-8bit
LFM2.5 24B A2Boffload19tok/sQ5_K_M
DeepSeek R1 Distill Qwen 14Boffload9tok/sQ5_K_M
Qwen 3.5 122B-A10Bwon't runoffload
Gemma 4 31Boffloadoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Boffloadoffload
Devstral Small 2 24Boffloadoffload
Qwen3 Next 80B-A3Bwon't runoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
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
GLM 4.5 Airwon'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 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 AMD Radeon RX 7600 XT 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 AMD Radeon RX 7600 XT or the NVIDIA Tesla P40?
At 64k context the NVIDIA Tesla P40 runs 45 of the models we track fully in memory and the AMD Radeon RX 7600 XT 30; only the NVIDIA Tesla P40 holds Qwen 3.8 27B.
Which is faster for local AI, the AMD Radeon RX 7600 XT or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA Tesla P40 is about 1.4× as fast as the AMD Radeon RX 7600 XT (estimated, median across models).
What is the price difference between the AMD Radeon RX 7600 XT and the NVIDIA Tesla P40?
In the US the AMD Radeon RX 7600 XT costs $410 at eBay (used) and the NVIDIA Tesla P40 $405 at eBay: the NVIDIA Tesla P40 is $5 cheaper.

More comparisons