readygpu

NVIDIA GeForce RTX 4080 Super vs NVIDIA GeForce RTX 5080

For running models locally, priced in India. At 32k context the first runs 13 models fully in memory, the second 13.

In short

Both have 16 GB of memory for models; the NVIDIA GeForce RTX 4080 Super has 736 GB/s of bandwidth and the NVIDIA GeForce RTX 5080 960 GB/s. At 32k context both run the same 13 models we track fully in memory. On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.3× as fast as the NVIDIA GeForce RTX 4080 Super (estimated, median across models).

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

NVIDIA GeForce RTX 4080 Super

Not priced here

Add to build
NVIDIA GeForce RTX 5080

Not priced here

Add to build

Specifications

SpecNVIDIA GeForce RTX 4080 SuperNVIDIA GeForce RTX 5080
GPUGeForce RTX 4080 SuperGeForce RTX 5080
Memory16 GB GDDR6X16 GB GDDR7
Memory bus256-bit256-bit
Memory bandwidth736 GB/s960 GB/s
FP16 compute104 TFLOPS113 TFLOPS
SoftwareCUDACUDA
Board power320 W360 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 4080 SuperNVIDIA GeForce RTX 5080
gpt-oss 20B85tok/sMXFP4110tok/sMXFP4
Gemma 4 12B34tok/sQ8_044tok/sQ8_0
Qwen 3.5 9B43tok/sQ8_056tok/sQ8_0
Qwen3 14B32tok/sQ4_K_M41tok/sQ4_K_M
Ministral 3 14B30tok/sQ5_K_M40tok/sQ5_K_M
DeepSeek R1 0528 Qwen3 8B34tok/sQ8_044tok/sQ8_0
Qwen3 8B34tok/sQ8_044tok/sQ8_0
Qwen 3.5 4B81tok/sQ8_0106tok/sQ8_0
Ministral 3 8B34tok/sQ8_044tok/sQ8_0
Granite 4.2 8B31tok/sQ8_041tok/sQ8_0
Gemma 4 E4B50tok/sQ8_065tok/sQ8_0
LFM2.5 8B-A1B102tok/sQ8_0134tok/sQ8_0
Llama 3.1 8B42tok/sQ6_K55tok/sQ6_K
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadoffload
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
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Phi-4 14Boffloadoffload
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
Llama 3.3 70Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 4080 Super or the NVIDIA GeForce RTX 5080?
Choose the NVIDIA GeForce RTX 5080 for speed.
Which can run bigger models, the NVIDIA GeForce RTX 4080 Super or the NVIDIA GeForce RTX 5080?
At 32k context both run the same 13 models we track fully in memory.
Which is faster for local AI, the NVIDIA GeForce RTX 4080 Super or the NVIDIA GeForce RTX 5080?
On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.3× as fast as the NVIDIA GeForce RTX 4080 Super (estimated, median across models).

More comparisons