readygpu

NVIDIA GeForce RTX 4060 Ti 8GB vs NVIDIA GeForce RTX 5050

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

In short

Both have 8 GB of memory for models; the NVIDIA GeForce RTX 4060 Ti 8GB has 288 GB/s of bandwidth and the NVIDIA GeForce RTX 5050 320 GB/s. At 8k context both run the same 26 models we track fully in memory. On the models both run fully in memory, the NVIDIA GeForce RTX 5050 is about 1.1× as fast as the NVIDIA GeForce RTX 4060 Ti 8GB (estimated, median across models). In the US the NVIDIA GeForce RTX 4060 Ti 8GB costs $440 at eBay and the NVIDIA GeForce RTX 5050 $380 at eBay: the NVIDIA GeForce RTX 5050 is $60 cheaper.

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

NVIDIA GeForce RTX 4060 Ti 8GB

$440

eBay

Add to build
NVIDIA GeForce RTX 5050

$380

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4060 Ti 8GBNVIDIA GeForce RTX 5050
GPUGeForce RTX 4060 Ti 8GBGeForce RTX 5050
Memory8 GB GDDR68 GB GDDR6
Memory bus128-bit128-bit
Memory bandwidth288 GB/s320 GB/s
FP16 compute22.065 TFLOPS13.169 TFLOPS
SoftwareCUDACUDA
Board power160 W130 W
PCIe generationGen 4Gen 5
PCIe lanesx8x8

What each runs

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

ModelNVIDIA GeForce RTX 4060 Ti 8GBNVIDIA GeForce RTX 5050
Qwen 3.5 9B26tok/sQ5_K_M29tok/sQ5_K_M
DeepSeek R1 0528 Qwen3 8B25tok/sQ5_K_M28tok/sQ5_K_M
Qwen3 8B25tok/sQ5_K_M28tok/sQ5_K_M
Qwen 3.5 4B37tok/sQ8_041tok/sQ8_0
Ministral 3 8B28tok/sQ4_K_M31tok/sQ4_K_M
Granite 4.2 8B26tok/sQ4_K_M29tok/sQ4_K_M
Gemma 4 E4B31tok/sQ5_K_M35tok/sQ5_K_M
LFM2.5 8B-A1B93tok/sUD-Q5_K_M103tok/sUD-Q5_K_M
Llama 3.1 8B26tok/sQ5_K_M29tok/sQ5_K_M
Qwen2.5 0.5B283tok/sQ8_0314tok/sQ8_0
Qwen3.5 0.8B192tok/sQ8_0213tok/sQ8_0
Qwen3.5 2B115tok/sQ5_K_M128tok/sQ5_K_M
LFM3 1.7B91tok/sQ8_0101tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B84tok/sQ8_093tok/sQ8_0
MiniCPM5 2B59tok/sQ8_065tok/sQ8_0
LFM2.5 2.6B53tok/sQ8_059tok/sQ8_0
LFM2.5 VL 3B53tok/sQ8_059tok/sQ8_0
Spark X2.5 4B53tok/smlx-4bit58tok/smlx-4bit
granite vision 4.1 4b42tok/sQ8_046tok/sQ8_0
Ministral 3 3B Instruct 251240tok/sQ8_044tok/sQ8_0
granite 4.2 3b39tok/sQ8_044tok/sQ8_0
FrogNano 4B 260936tok/sQ8_040tok/sQ8_0
Ministral 3 8B Reasoning 251228tok/sQ4_K_M31tok/sQ4_K_M
GLM 4.6V Flash28tok/sQ4_K_M31tok/sQ4_K_M
DeepSeek R1 Distill Qwen 7B27tok/sQ6_K30tok/sQ6_K
DeepSeek R1 Distill Llama 8B26tok/sQ5_K_M29tok/sQ5_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
Gemma 4 12Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
Gemma 3 27Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Ministral 3 14Boffloadoffload
Qwen3 14Boffloadoffload
Phi-4 14Boffloadoffload
Mellum2.1 12B A2.5B Thinkingoffloadoffload
Kimi VL A3B Thinking 2506offloadoffload
LFM2.5 24B A2Boffloadoffload
Kimi VL A3Boffloadoffload
GLM 4 9B 0414offloadoffload
Ministral 3 14B Reasoning 2512offloadoffload
DeepSeek R1 Distill Qwen 14Boffloadoffload
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 Ti 8GB or the NVIDIA GeForce RTX 5050?
Choose the NVIDIA GeForce RTX 5050 for speed. Choose the NVIDIA GeForce RTX 5050 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4060 Ti 8GB or the NVIDIA GeForce RTX 5050?
At 8k context both run the same 26 models we track fully in memory.
Which is faster for local AI, the NVIDIA GeForce RTX 4060 Ti 8GB or the NVIDIA GeForce RTX 5050?
On the models both run fully in memory, the NVIDIA GeForce RTX 5050 is about 1.1× 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 5050?
In the US the NVIDIA GeForce RTX 4060 Ti 8GB costs $440 at eBay and the NVIDIA GeForce RTX 5050 $380 at eBay: the NVIDIA GeForce RTX 5050 is $60 cheaper.

More comparisons

More hardware for local AI