readygpu

NVIDIA GeForce RTX 4060 vs NVIDIA GeForce RTX 4070

For running models locally, priced in the US. At 8k context the first runs 26 models fully in memory, the second 35.

In short

The NVIDIA GeForce RTX 4070 has more memory for models: 12 GB against 8 GB. At 8k context the NVIDIA GeForce RTX 4070 runs 35 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 26; only the NVIDIA GeForce RTX 4070 holds Gemma 4 12B. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 is about 1.9× as fast as the NVIDIA GeForce RTX 4060 (estimated, median across models). In the US the NVIDIA GeForce RTX 4060 costs $530 at eBay and the NVIDIA GeForce RTX 4070 $570 at eBay: the NVIDIA GeForce RTX 4060 is $40 cheaper.

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

NVIDIA GeForce RTX 4060

$530

eBay

Add to build
NVIDIA GeForce RTX 4070

$570

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4060NVIDIA GeForce RTX 4070
GPUGeForce RTX 4060GeForce RTX 4070
Memory8 GB GDDR612 GB GDDR6X
Memory bus128-bit192-bit
Memory bandwidth272 GB/s504.2 GB/s
FP16 compute15.114 TFLOPS29.146 TFLOPS
SoftwareCUDACUDA
Board power115 W200 W
PCIe generationGen 4Gen 4
PCIe lanesx8x16

What each runs

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

ModelNVIDIA GeForce RTX 4060NVIDIA GeForce RTX 4070
Gemma 4 12Boffload31tok/sQ6_K
Qwen 3.5 9B25tok/sQ5_K_M32tok/sQ8_0
Ministral 3 14Boffload29tok/sQ5_K_M
Qwen3 14Boffload30tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8B24tok/sQ5_K_M32tok/sQ8_0
Qwen3 8B24tok/sQ5_K_M32tok/sQ8_0
Phi-4 14Boffload30tok/sQ4_K_M
Qwen 3.5 4B35tok/sQ8_065tok/sQ8_0
Ministral 3 8B27tok/sQ4_K_M31tok/sQ8_0
Granite 4.2 8B25tok/sQ4_K_M29tok/sQ8_0
Gemma 4 E4B29tok/sQ5_K_M37tok/sQ8_0
LFM2.5 8B-A1B88tok/sUD-Q5_K_M128tok/sQ8_0
Llama 3.1 8B25tok/sQ5_K_M41tok/sQ6_K
Qwen2.5 0.5B267tok/sQ8_0495tok/sQ8_0
Qwen3.5 0.8B181tok/sQ8_0336tok/sQ8_0
Qwen3.5 2B109tok/sQ5_K_M201tok/sQ5_K_M
LFM3 1.7B86tok/sQ8_0160tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B79tok/sQ8_0147tok/sQ8_0
MiniCPM5 2B56tok/sQ8_0103tok/sQ8_0
LFM2.5 2.6B50tok/sQ8_093tok/sQ8_0
LFM2.5 VL 3B50tok/sQ8_093tok/sQ8_0
Spark X2.5 4B50tok/smlx-4bit92tok/smlx-4bit
granite vision 4.1 4b39tok/sQ8_073tok/sQ8_0
Ministral 3 3B Instruct 251237tok/sQ8_069tok/sQ8_0
granite 4.2 3b37tok/sQ8_069tok/sQ8_0
FrogNano 4B 260934tok/sQ8_063tok/sQ8_0
Ministral 3 8B Reasoning 251227tok/sQ4_K_M31tok/sQ8_0
GLM 4.6V Flash26tok/sQ4_K_M30tok/sQ8_0
DeepSeek R1 Distill Qwen 7B25tok/sQ6_K37tok/sQ8_0
DeepSeek R1 Distill Llama 8B25tok/sQ5_K_M33tok/sQ8_0
Mellum2.1 12B A2.5B Thinkingoffload85tok/sQ5_K_M
Kimi VL A3B Thinking 2506offload86tok/sQ4_K_M
GLM 4 9B 0414offload36tok/smlx-5bit
Ministral 3 14B Reasoning 2512offload29tok/sQ5_K_M
DeepSeek R1 Distill Qwen 14Boffload30tok/sQ4_K_M
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
Mistral Small 3.2 24Boffloadoffload
Gemma 3 27Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
LFM2.5 24B A2Boffloadoffload
Kimi VL A3Boffloadoffload
GLM 4.1V 9B Thinkingoffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
Muse Glimmer 30Boffloadoffload
granite 4.2 30boffloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
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 4060 or the NVIDIA GeForce RTX 4070?
Choose the NVIDIA GeForce RTX 4070 to run bigger models. Choose the NVIDIA GeForce RTX 4070 for speed. Choose the NVIDIA GeForce RTX 4060 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4060 or the NVIDIA GeForce RTX 4070?
At 8k context the NVIDIA GeForce RTX 4070 runs 35 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 26; only the NVIDIA GeForce RTX 4070 holds Gemma 4 12B.
Which is faster for local AI, the NVIDIA GeForce RTX 4060 or the NVIDIA GeForce RTX 4070?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 is about 1.9× as fast as the NVIDIA GeForce RTX 4060 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4060 and the NVIDIA GeForce RTX 4070?
In the US the NVIDIA GeForce RTX 4060 costs $530 at eBay and the NVIDIA GeForce RTX 4070 $570 at eBay: the NVIDIA GeForce RTX 4060 is $40 cheaper.

More comparisons

More hardware for local AI