readygpu

Intel Arc Pro B60 vs NVIDIA GeForce RTX 3090 Ti

For running models locally, priced in the US. At 64k context the first runs 44 models fully in memory, the second 45.

In short

Both have 24 GB of memory for models; the Intel Arc Pro B60 has 456 GB/s of bandwidth and the NVIDIA GeForce RTX 3090 Ti 1,008 GB/s. At 64k context the NVIDIA GeForce RTX 3090 Ti runs 45 of the models we track fully in memory and the Intel Arc Pro B60 44; only the NVIDIA GeForce RTX 3090 Ti holds Nemotron 3.5 Lightning 30B-A3B. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 2.7× as fast as the Intel Arc Pro B60 (estimated, median across models). In the US the Intel Arc Pro B60 costs $650 at Amazon and the NVIDIA GeForce RTX 3090 Ti $995 at Amazon: the Intel Arc Pro B60 is $345 cheaper.

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

Intel Arc Pro B60

$650

Amazon

Add to build
NVIDIA GeForce RTX 3090 Ti

$995

Amazon

Add to build

Specifications

SpecIntel Arc Pro B60NVIDIA GeForce RTX 3090 Ti
GPUArc Pro B60GeForce RTX 3090 Ti
Memory24 GB GDDR624 GB GDDR6X
Memory bus192-bit384-bit
Memory bandwidth456 GB/s1,008 GB/s
FP16 compute98.5 TFLOPS80 TFLOPS
SoftwareSYCL / oneAPICUDA
Board power200 W450 W
PCIe generationGen 5Gen 4
PCIe lanesx8x16

What each runs

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

ModelIntel Arc Pro B60NVIDIA GeForce RTX 3090 Ti
Qwen 3.8 27B10tok/sQ4_K_M29tok/sQ4_K_M
Qwen 3.6 27B11tok/sQ4_K_M26tok/sQ5_K_M
Qwen 3.6 35B-A3B39tok/sUD-Q4_K_M115tok/sQ4_K_M
Qwen 3.5 27B11tok/sQ4_K_M30tok/sQ4_K_M
Gemma 4 26B-A4B26tok/sUD-Q5_K_M78tok/sUD-Q5_K_M
Qwen 3.5 35B-A3B39tok/sQ4_K_M116tok/sQ4_K_M
GLM 4.7 Flash19tok/sQ4_K_M57tok/sQ4_K_M
Nemotron 3.5 Lightning 30B-A3Boffload141tok/sMXFP4
gpt-oss 20B31tok/sMXFP493tok/sMXFP4
Gemma 4 12B16tok/sQ8_044tok/sQ8_0
Qwen 3.5 9B19tok/sQ8_053tok/sQ8_0
Gemma 3 27B10tok/sQ4_K_M28tok/sQ4_K_M
Ministral 3 14B10tok/sQ6_K29tok/sQ6_K
Qwen3 14B10tok/sQ6_K27tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B12tok/sQ8_034tok/sQ8_0
Qwen3 8B12tok/sQ8_034tok/sQ8_0
Phi-4 14B10tok/sQ4_K_M26tok/sQ5_K_M
Qwen 3.5 4B34tok/sQ8_094tok/sQ8_0
Ministral 3 8B13tok/sQ8_034tok/sQ8_0
Granite 4.2 8B11tok/sQ8_031tok/sQ8_0
Gemma 4 E4B23tok/sQ8_062tok/sQ8_0
LFM2.5 8B-A1B29tok/sQ8_088tok/sQ8_0
Llama 3.1 8B15tok/sQ6_K41tok/sQ6_K
Qwen2.5 0.5B171tok/sQ8_0468tok/sQ8_0
Qwen3.5 0.8B139tok/sQ8_0382tok/sQ8_0
Qwen3.5 2B101tok/sQ5_K_M277tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B60tok/sQ8_0166tok/sQ8_0
MiniCPM5 2B42tok/sQ8_0114tok/sQ8_0
Spark X2.5 4B41tok/smlx-4bit113tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking34tok/sQ8_0103tok/sQ8_0
FrogNano 4B 260933tok/sQ8_092tok/sQ8_0
LFM2.5 2.6B33tok/sQ8_091tok/sQ8_0
LFM2.5 VL 3B33tok/sQ8_091tok/sQ8_0
granite vision 4.1 4b25tok/sQ8_070tok/sQ8_0
granite 4.2 3b25tok/sQ8_068tok/sQ8_0
Kimi VL A3B Thinking 250624tok/sQ8_073tok/sQ8_0
Kimi VL A3B24tok/smlx-8bit71tok/smlx-8bit
GLM 4 9B 041421tok/smlx-5bit57tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B19tok/sQ8_053tok/sQ8_0
LFM2.5 24B A2B19tok/sQ4_K_M54tok/sQ5_K_M
GLM 4.6V Flash18tok/sQ8_049tok/sQ8_0
GLM 4.1V 9B Thinking16tok/smlx-8bit43tok/smlx-8bit
DeepSeek R1 Distill Llama 8B13tok/sQ8_037tok/sQ8_0
Ministral 3 8B Reasoning 251213tok/sQ8_034tok/sQ8_0
DeepSeek R1 Distill Qwen 14B10tok/sQ5_K_M27tok/sQ5_K_M
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadoffload
Qwen3 Next 80B-A3Boffloadoffload
Devstral Small 2 24Boffloadoffload
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 Intel Arc Pro B60 or the NVIDIA GeForce RTX 3090 Ti?
Choose the NVIDIA GeForce RTX 3090 Ti to run bigger models. Choose the NVIDIA GeForce RTX 3090 Ti for speed. Choose the Intel Arc Pro B60 to spend less.
Which can run bigger models, the Intel Arc Pro B60 or the NVIDIA GeForce RTX 3090 Ti?
At 64k context the NVIDIA GeForce RTX 3090 Ti runs 45 of the models we track fully in memory and the Intel Arc Pro B60 44; only the NVIDIA GeForce RTX 3090 Ti holds Nemotron 3.5 Lightning 30B-A3B.
Which is faster for local AI, the Intel Arc Pro B60 or the NVIDIA GeForce RTX 3090 Ti?
On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 2.7× as fast as the Intel Arc Pro B60 (estimated, median across models).
What is the price difference between the Intel Arc Pro B60 and the NVIDIA GeForce RTX 3090 Ti?
In the US the Intel Arc Pro B60 costs $650 at Amazon and the NVIDIA GeForce RTX 3090 Ti $995 at Amazon: the Intel Arc Pro B60 is $345 cheaper.

More comparisons