readygpu

NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 4080 Super

For running models locally, priced in the UK. At 32k context the first runs 48 models fully in memory, the second 30.

In short

The NVIDIA GeForce RTX 3090 Ti has more memory for models: 24 GB against 16 GB. At 32k context the NVIDIA GeForce RTX 3090 Ti runs 48 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 30; only the NVIDIA GeForce RTX 3090 Ti holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 1.4× as fast as the NVIDIA GeForce RTX 4080 Super (estimated, median across models). In the UK the NVIDIA GeForce RTX 3090 Ti costs £2,199 at Amazon and the NVIDIA GeForce RTX 4080 Super £1,395 at Amazon: the NVIDIA GeForce RTX 4080 Super is £804 cheaper.

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

NVIDIA GeForce RTX 3090 Ti

£2,199

Amazon

Add to build
NVIDIA GeForce RTX 4080 Super

£1,395

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 3090 TiNVIDIA GeForce RTX 4080 Super
GPUGeForce RTX 3090 TiGeForce RTX 4080 Super
Memory24 GB GDDR6X16 GB GDDR6X
Memory bus384-bit256-bit
Memory bandwidth1,008 GB/s736 GB/s
FP16 compute80 TFLOPS104 TFLOPS
SoftwareCUDACUDA
Board power450 W320 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 3090 TiNVIDIA GeForce RTX 4080 Super
Qwen 3.8 27B27tok/sQ5_K_Moffload
Qwen 3.6 27B29tok/sQ5_K_Moffload
Gemma 4 31B29tok/sQ4_K_Moffload
Qwen 3.6 35B-A3B145tok/sQ4_K_Moffload
Qwen 3.5 27B29tok/sQ5_K_Moffload
Gemma 4 26B-A4B84tok/sUD-Q6_Koffload
Qwen 3.5 35B-A3B146tok/sQ4_K_Moffload
GLM 4.7 Flash70tok/sQ5_K_Moffload
Devstral Small 2 24B28tok/sQ5_K_Moffload
gpt-oss 20B116tok/sMXFP485tok/sMXFP4
Qwen3 Coder 30B-A3B74tok/sQ4_K_Moffload
Gemma 4 12B46tok/sQ8_034tok/sQ8_0
Qwen 3.5 9B59tok/sQ8_043tok/sQ8_0
Mistral Small 3.2 24B28tok/sQ5_K_Moffload
Gemma 3 27B28tok/sQ5_K_Moffload
Ministral 3 14B32tok/sQ8_030tok/sQ5_K_M
Qwen3 14B30tok/sQ8_032tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8B46tok/sQ8_034tok/sQ8_0
Qwen3 8B46tok/sQ8_034tok/sQ8_0
Phi-4 14B28tok/sQ8_0offload
Qwen 3.5 4B112tok/sQ8_081tok/sQ8_0
Ministral 3 8B46tok/sQ8_034tok/sQ8_0
Granite 4.2 8B43tok/sQ8_031tok/sQ8_0
Gemma 4 E4B68tok/sQ8_050tok/sQ8_0
LFM2.5 8B-A1B140tok/sQ8_0102tok/sQ8_0
Llama 3.1 8B57tok/sQ6_K42tok/sQ6_K
Qwen2.5 0.5B669tok/sQ8_0489tok/sQ8_0
Qwen3.5 0.8B507tok/sQ8_0370tok/sQ8_0
Qwen3.5 2B337tok/sQ5_K_M246tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B221tok/sQ8_0161tok/sQ8_0
MiniCPM5 2B153tok/sQ8_0112tok/sQ8_0
LFM2.5 2.6B128tok/sQ8_093tok/sQ8_0
LFM2.5 VL 3B128tok/sQ8_093tok/sQ8_0
Mellum2.1 12B A2.5B Thinking118tok/sQ8_086tok/sQ8_0
granite vision 4.1 4b99tok/sQ8_072tok/sQ8_0
granite 4.2 3b95tok/sQ8_069tok/sQ8_0
Kimi VL A3B88tok/smlx-8bit77tok/smlx-6bit
LFM2.5 24B A2B84tok/sQ6_Koffload
DeepSeek R1 Distill Qwen 7B63tok/sQ8_046tok/sQ8_0
GLM 4.6V Flash55tok/sQ8_040tok/sQ8_0
DeepSeek R1 Distill Llama 8B49tok/sQ8_036tok/sQ8_0
GLM 4.1V 9B Thinking48tok/smlx-8bit35tok/smlx-8bit
Ministral 3 8B Reasoning 251246tok/sQ8_034tok/sQ8_0
DeepSeek R1 Distill Qwen 14B28tok/sQ8_030tok/sQ4_K_M
Devstral Small 250728tok/sQ5_K_Moffload
Magistral Small 250628tok/sQ5_K_Moffload
Magistral Small 250728tok/sQ5_K_Moffload
Magistral Small 250928tok/sQ5_K_Moffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadwon't run
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
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
Nemotron 3 Super 120B-A12Bwon't runwon't run
gpt-oss 120Bwon'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 V3 0324won't runwon't run
DeepSeek V3.1won'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 4.5Vwon't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won'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 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 3090 Ti or the NVIDIA GeForce RTX 4080 Super?
Choose the NVIDIA GeForce RTX 3090 Ti to run bigger models. Choose the NVIDIA GeForce RTX 3090 Ti for speed. Choose the NVIDIA GeForce RTX 4080 Super to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 3090 Ti or the NVIDIA GeForce RTX 4080 Super?
At 32k context the NVIDIA GeForce RTX 3090 Ti runs 48 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 30; only the NVIDIA GeForce RTX 3090 Ti holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 3090 Ti or the NVIDIA GeForce RTX 4080 Super?
On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 1.4× as fast as the NVIDIA GeForce RTX 4080 Super (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 3090 Ti and the NVIDIA GeForce RTX 4080 Super?
In the UK the NVIDIA GeForce RTX 3090 Ti costs £2,199 at Amazon and the NVIDIA GeForce RTX 4080 Super £1,395 at Amazon: the NVIDIA GeForce RTX 4080 Super is £804 cheaper.

More comparisons