readygpu

NVIDIA GeForce RTX 4060 Ti 8GB vs NVIDIA GeForce RTX 4090

For running models locally, priced in Germany. At 8k context the first runs 26 models fully in memory, the second 61.

In short

The NVIDIA GeForce RTX 4090 has more memory for models: 24 GB against 8 GB. At 8k context the NVIDIA GeForce RTX 4090 runs 61 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 Ti 8GB 26; only the NVIDIA GeForce RTX 4090 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 3.5× as fast as the NVIDIA GeForce RTX 4060 Ti 8GB (estimated, median across models). In Germany the NVIDIA GeForce RTX 4060 Ti 8GB costs 425 € at Amazon and the NVIDIA GeForce RTX 4090 4.385 € at eBay: the NVIDIA GeForce RTX 4060 Ti 8GB is 3.960 € cheaper.

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

NVIDIA GeForce RTX 4060 Ti 8GB

425 €

Amazon

Add to build
NVIDIA GeForce RTX 4090

4.385 €

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4060 Ti 8GBNVIDIA GeForce RTX 4090
GPUGeForce RTX 4060 Ti 8GBGeForce RTX 4090
Memory8 GB GDDR624 GB GDDR6X
Memory bus128-bit384-bit
Memory bandwidth288 GB/s1,008 GB/s
FP16 compute22.065 TFLOPS165 TFLOPS
SoftwareCUDACUDA
Board power160 W450 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 4060 Ti 8GBNVIDIA GeForce RTX 4090
Qwen 3.8 27Boffload28tok/sUD-Q6_K
Qwen 3.6 27Boffload27tok/sQ6_K
Gemma 4 31Boffload27tok/sQ5_K_M
Qwen 3.6 35B-A3Boffload179tok/sQ4_K_M
Qwen 3.5 27Boffload27tok/sQ6_K
Gemma 4 26B-A4Boffload95tok/sUD-Q6_K
Qwen 3.5 35B-A3Boffload181tok/sQ4_K_M
GLM 4.7 Flashoffload94tok/sQ5_K_M
Devstral Small 2 24Boffload30tok/sQ6_K
Nemotron 3.5 Lightning 30B-A3Boffload163tok/sMXFP4
gpt-oss 20Boffload142tok/sMXFP4
Qwen3 Coder 30B-A3Boffload128tok/sQ5_K_M
Qwen3 32Boffload29tok/sQ4_K_M
Gemma 4 12Boffload48tok/sQ8_0
Qwen 3.5 9B26tok/sQ5_K_M64tok/sQ8_0
Mistral Small 3.2 24Boffload30tok/sQ6_K
Gemma 3 27Boffload27tok/sQ6_K
DeepSeek R1 Distill Qwen 32Boffload28tok/sQ4_K_M
Ministral 3 14Boffload40tok/sQ8_0
Qwen3 14Boffload37tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B25tok/sQ5_K_M63tok/sQ8_0
Qwen3 8B25tok/sQ5_K_M63tok/sQ8_0
Phi-4 14Boffload36tok/sQ8_0
Qwen 3.5 4B37tok/sQ8_0130tok/sQ8_0
Ministral 3 8B28tok/sQ4_K_M62tok/sQ8_0
Granite 4.2 8B26tok/sQ4_K_M59tok/sQ8_0
Gemma 4 E4B31tok/sQ5_K_M74tok/sQ8_0
LFM2.5 8B-A1B93tok/sUD-Q5_K_M256tok/sQ8_0
Llama 3.1 8B26tok/sQ5_K_M82tok/sQ6_K
Qwen2.5 0.5B283tok/sQ8_0989tok/sQ8_0
Qwen3.5 0.8B192tok/sQ8_0671tok/sQ8_0
Qwen3.5 2B115tok/sQ5_K_M402tok/sQ5_K_M
LFM3 1.7B91tok/sQ8_0320tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B84tok/sQ8_0294tok/sQ8_0
MiniCPM5 2B59tok/sQ8_0206tok/sQ8_0
LFM2.5 2.6B53tok/sQ8_0185tok/sQ8_0
LFM2.5 VL 3B53tok/sQ8_0185tok/sQ8_0
Spark X2.5 4B53tok/smlx-4bit184tok/smlx-4bit
granite vision 4.1 4b42tok/sQ8_0146tok/sQ8_0
Ministral 3 3B Instruct 251240tok/sQ8_0138tok/sQ8_0
granite 4.2 3b39tok/sQ8_0137tok/sQ8_0
FrogNano 4B 260936tok/sQ8_0127tok/sQ8_0
Ministral 3 8B Reasoning 251228tok/sQ4_K_M62tok/sQ8_0
GLM 4.6V Flash28tok/sQ4_K_M61tok/sQ8_0
DeepSeek R1 Distill Qwen 7B27tok/sQ6_K73tok/sQ8_0
DeepSeek R1 Distill Llama 8B26tok/sQ5_K_M65tok/sQ8_0
Mellum2.1 12B A2.5B Thinkingoffload133tok/sQ8_0
Kimi VL A3B Thinking 2506offload112tok/sQ8_0
LFM2.5 24B A2Boffload154tok/sQ6_K
Kimi VL A3Boffload107tok/smlx-8bit
GLM 4 9B 0414offload73tok/smlx-5bit
Ministral 3 14B Reasoning 2512offload40tok/sQ8_0
DeepSeek R1 Distill Qwen 14Boffload36tok/sQ8_0
GLM 4.1V 9B Thinkingoffload52tok/smlx-8bit
Devstral Small 2507offload35tok/sQ5_K_M
Magistral Small 2506offload30tok/sQ6_K
Magistral Small 2507offload35tok/sQ5_K_M
Magistral Small 2509offload35tok/sQ5_K_M
Muse Glimmer 30Boffload27tok/sQ6_K
granite 4.2 30boffload27tok/sQ5_K_M
Qwen3.8 27B OBLITERATEDoffload29tok/smlx-4bit
Qwen 3.5 122B-A10Bwon't runoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Bwon't runoffload
GLM 4.5 Airwon't runoffload
Qwen3 Next 80B-A3Bwon't runoffload
Kimi Linear 48B-A3Boffloadoffload
Llama 3.3 70Bwon't runoffload
DeepSeek R1 Distill Llama 70Bwon't runoffload
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
DeepSeek R1won't runwon't run
DeepSeek R1 0528won'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 Ti 8GB or the NVIDIA GeForce RTX 4090?
Choose the NVIDIA GeForce RTX 4090 to run bigger models. Choose the NVIDIA GeForce RTX 4090 for speed. Choose the NVIDIA GeForce RTX 4060 Ti 8GB to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4060 Ti 8GB or the NVIDIA GeForce RTX 4090?
At 8k context the NVIDIA GeForce RTX 4090 runs 61 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 Ti 8GB 26; only the NVIDIA GeForce RTX 4090 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 4060 Ti 8GB or the NVIDIA GeForce RTX 4090?
On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 3.5× as fast as the NVIDIA GeForce RTX 4060 Ti 8GB (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4060 Ti 8GB and the NVIDIA GeForce RTX 4090?
In Germany the NVIDIA GeForce RTX 4060 Ti 8GB costs 425 € at Amazon and the NVIDIA GeForce RTX 4090 4.385 € at eBay: the NVIDIA GeForce RTX 4060 Ti 8GB is 3.960 € cheaper.

More comparisons

More hardware for local AI