readygpu

NVIDIA GeForce RTX 4070 Ti Super vs NVIDIA RTX PRO 4000 Blackwell

For running models locally, priced in Germany. At 128k context the first runs 22 models fully in memory, the second 31.

In short

The NVIDIA RTX PRO 4000 Blackwell has more memory for models: 24 GB against 16 GB. At 128k context the NVIDIA RTX PRO 4000 Blackwell runs 31 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Ti Super 22; only the NVIDIA RTX PRO 4000 Blackwell holds Gemma 4 26B-A4B. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Ti Super and the NVIDIA RTX PRO 4000 Blackwell are about as fast as each other (estimated).

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

NVIDIA GeForce RTX 4070 Ti Super

1.458 €

Amazon

Add to build
NVIDIA RTX PRO 4000 Blackwell

Not priced here

Add to build

Specifications

SpecNVIDIA GeForce RTX 4070 Ti SuperNVIDIA RTX PRO 4000 Blackwell
GPUGeForce RTX 4070 Ti SuperRTX PRO 4000 Blackwell
Memory16 GB GDDR6X24 GB GDDR7
Memory bus256-bit192-bit
Memory bandwidth672 GB/s672 GB/s
FP16 compute88 TFLOPS46.9 TFLOPS
SoftwareCUDACUDA
Board power285 W145 W
PCIe generationGen 4Gen 5
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 4070 Ti SuperNVIDIA RTX PRO 4000 Blackwell
Gemma 4 26B-A4Boffload43tok/sQ5_K_M
gpt-oss 20B45tok/sQ4_K_M44tok/sMXFP4
Gemma 4 12B34tok/sQ6_K28tok/sQ8_0
Qwen 3.5 9B30tok/sQ8_030tok/sQ8_0
Qwen 3.5 4B47tok/sQ8_047tok/sQ8_0
Ministral 3 8Boffload18tok/sQ4_K_M
Gemma 4 E4B35tok/sQ8_035tok/sQ8_0
LFM2.5 8B-A1B34tok/sUD-Q6_K33tok/sQ8_0
Llama 3.1 8Boffload18tok/sQ5_K_M
Qwen2.5 0.5B195tok/sQ8_0195tok/sQ8_0
Qwen3.5 0.8B171tok/sQ8_0171tok/sQ8_0
Qwen3.5 2B136tok/sQ5_K_M136tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B74tok/sQ8_074tok/sQ8_0
Mellum2.1 12B A2.5B Thinking55tok/sQ8_055tok/sQ8_0
Spark X2.5 4B53tok/smlx-4bit53tok/smlx-4bit
MiniCPM5 2B50tok/sQ8_050tok/sQ8_0
FrogNano 4B 260947tok/sQ8_047tok/sQ8_0
Kimi VL A3B Thinking 250642tok/sQ4_K_M35tok/sQ8_0
LFM2.5 2.6B38tok/sQ8_038tok/sQ8_0
LFM2.5 VL 3B38tok/sQ8_038tok/sQ8_0
GLM 4.6V Flash36tok/sQ4_K_M27tok/sQ8_0
GLM 4 9B 041431tok/smlx-5bit31tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B30tok/sQ6_K27tok/sQ8_0
granite vision 4.1 4b29tok/sQ8_029tok/sQ8_0
granite 4.2 3b29tok/sQ8_029tok/sQ8_0
Kimi VL A3Boffload34tok/smlx-8bit
Ministral 3 3B Instruct 2512offload24tok/sQ8_0
GLM 4.1V 9B Thinkingoffload24tok/smlx-8bit
Muse Glimmer 30Boffload19tok/sQ5_K_M
DeepSeek R1 Distill Llama 8Boffload18tok/sQ5_K_M
Ministral 3 8B Reasoning 2512offload18tok/sQ4_K_M
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Bwon't runoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Bwon't runoffload
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
Ministral 3 14Boffloadoffload
Qwen3 14Boffloadoffload
DeepSeek R1 0528 Qwen3 8Boffloadoffload
Qwen3 8Boffloadoffload
Phi-4 14Boffloadoffload
Granite 4.2 8Boffloadoffload
LFM2.5 24B A2Boffloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
Ministral 3 14B Reasoning 2512offloadoffload
DeepSeek R1 Distill Qwen 14Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
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
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Qwen3 32Bwon't runwon't run
DeepSeek R1 Distill Qwen 32Bwon'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 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 4.5Vwon'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
granite 4.2 30bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 4070 Ti Super or the NVIDIA RTX PRO 4000 Blackwell?
Choose the NVIDIA RTX PRO 4000 Blackwell to run bigger models.
Which can run bigger models, the NVIDIA GeForce RTX 4070 Ti Super or the NVIDIA RTX PRO 4000 Blackwell?
At 128k context the NVIDIA RTX PRO 4000 Blackwell runs 31 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Ti Super 22; only the NVIDIA RTX PRO 4000 Blackwell holds Gemma 4 26B-A4B.
Which is faster for local AI, the NVIDIA GeForce RTX 4070 Ti Super or the NVIDIA RTX PRO 4000 Blackwell?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Ti Super and the NVIDIA RTX PRO 4000 Blackwell are about as fast as each other (estimated).

More comparisons

More hardware for local AI