readygpu

NVIDIA GeForce RTX 4070 vs NVIDIA GeForce RTX 4070 Super

For running models locally, priced in Canada. At 64k context the first runs 21 models fully in memory, the second 21.

In short

Both have 12 GB of memory for models; the NVIDIA GeForce RTX 4070 has 504.2 GB/s of bandwidth and the NVIDIA GeForce RTX 4070 Super 504 GB/s. At 64k context both run the same 21 models we track fully in memory. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 and the NVIDIA GeForce RTX 4070 Super are about as fast as each other (estimated). In Canada the NVIDIA GeForce RTX 4070 costs $1,230 at Amazon and the NVIDIA GeForce RTX 4070 Super $1,400 at Amazon: the NVIDIA GeForce RTX 4070 is $170 cheaper.

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

NVIDIA GeForce RTX 4070

$1,230

Amazon

Add to build
NVIDIA GeForce RTX 4070 Super

$1,400

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 4070NVIDIA GeForce RTX 4070 Super
GPUGeForce RTX 4070GeForce RTX 4070 Super
Memory12 GB GDDR6X12 GB GDDR6X
Memory bus192-bit192-bit
Memory bandwidth504.2 GB/s504 GB/s
FP16 compute29.146 TFLOPS71 TFLOPS
SoftwareCUDACUDA
Board power200 W220 W
PCIe generationGen 4Gen 4
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 4070NVIDIA GeForce RTX 4070 Super
Gemma 4 12B32tok/sQ5_K_M32tok/sQ5_K_M
Qwen 3.5 9B32tok/sQ6_K32tok/sQ6_K
Qwen 3.5 4B47tok/sQ8_047tok/sQ8_0
Gemma 4 E4B31tok/sQ8_031tok/sQ8_0
LFM2.5 8B-A1B46tok/sUD-Q6_K46tok/sUD-Q6_K
Qwen2.5 0.5B234tok/sQ8_0234tok/sQ8_0
Qwen3.5 0.8B191tok/sQ8_0191tok/sQ8_0
Qwen3.5 2B138tok/sQ5_K_M138tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B83tok/sQ8_083tok/sQ8_0
Mellum2.1 12B A2.5B Thinking62tok/sQ5_K_M62tok/sQ5_K_M
MiniCPM5 2B57tok/sQ8_057tok/sQ8_0
Spark X2.5 4B57tok/smlx-4bit57tok/smlx-4bit
FrogNano 4B 260946tok/sQ8_046tok/sQ8_0
LFM2.5 2.6B45tok/sQ8_045tok/sQ8_0
LFM2.5 VL 3B45tok/sQ8_045tok/sQ8_0
GLM 4.6V Flash35tok/sQ4_K_M35tok/sQ4_K_M
granite vision 4.1 4b35tok/sQ8_035tok/sQ8_0
granite 4.2 3b34tok/sQ8_034tok/sQ8_0
DeepSeek R1 Distill Qwen 7B31tok/sQ6_K31tok/sQ6_K
Ministral 3 3B Instruct 251229tok/sQ8_029tok/sQ8_0
GLM 4 9B 041429tok/smlx-5bit29tok/smlx-5bit
Qwen 3.8 27Boffloadoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Gemma 4 26B-A4Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
gpt-oss 20Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Ministral 3 14Boffloadoffload
Qwen3 14Boffloadoffload
DeepSeek R1 0528 Qwen3 8Boffloadoffload
Qwen3 8Boffloadoffload
Phi-4 14Boffloadoffload
Ministral 3 8Boffloadoffload
Granite 4.2 8Boffloadoffload
Llama 3.1 8Boffloadoffload
Kimi VL A3B Thinking 2506offloadoffload
Kimi VL A3Boffloadoffload
DeepSeek R1 Distill Llama 8Boffloadoffload
Ministral 3 8B Reasoning 2512offloadoffload
GLM 4.1V 9B Thinkingoffloadoffload
LFM2.5 24B A2Boffloadoffload
Muse Glimmer 30Boffloadoffload
Ministral 3 14B Reasoning 2512offloadoffload
DeepSeek R1 Distill Qwen 14Boffloadoffload
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
Qwen 3.5 122B-A10Bwon'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
Mistral Small 4 119Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon'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

Questions

Which is better for local AI, the NVIDIA GeForce RTX 4070 or the NVIDIA GeForce RTX 4070 Super?
Choose the NVIDIA GeForce RTX 4070 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4070 or the NVIDIA GeForce RTX 4070 Super?
At 64k context both run the same 21 models we track fully in memory.
Which is faster for local AI, the NVIDIA GeForce RTX 4070 or the NVIDIA GeForce RTX 4070 Super?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 and the NVIDIA GeForce RTX 4070 Super are about as fast as each other (estimated).
What is the price difference between the NVIDIA GeForce RTX 4070 and the NVIDIA GeForce RTX 4070 Super?
In Canada the NVIDIA GeForce RTX 4070 costs $1,230 at Amazon and the NVIDIA GeForce RTX 4070 Super $1,400 at Amazon: the NVIDIA GeForce RTX 4070 is $170 cheaper.

More comparisons

More hardware for local AI