Skip to content

NVIDIA GeForce RTX 4080

NVIDIA · 16GB GDDR6X · Can run 49 models

Buy Amazon
Manufacturer NVIDIA
VRAM 16 GB
Memory Type GDDR6X
Architecture Ada Lovelace
CUDA Cores 9,728
Tensor Cores 304
Bandwidth 717 GB/s
TDP 320W
MSRP $1,199
Released Nov 16, 2022

AI Notes

The RTX 4080 is a capable GPU for running local AI models. With 16GB of GDDR6X VRAM, it handles 13B-parameter models well and can run some 30B models with Q4 quantization. Tensor cores accelerate inference, making it suitable for interactive AI applications.

Compatible Models

Model Parameters Best Quant VRAM Used Fit Est. Speed
Qwen 3 0.6B 600M Q4_K_M 2.5 GB Runs ~287 tok/s
Gemma 3 1B 1B Q8_0 2 GB Runs ~359 tok/s
Llama 3.2 1B 1B Q8_0 3 GB Runs ~239 tok/s
DeepSeek R1 1.5B 1.5B Q8_0 3 GB Runs ~239 tok/s
Gemma 2 2B 2B Q8_0 4 GB Runs ~179 tok/s
Gemma 3n E2B 2B Q4_K_M 3.3 GB Runs ~217 tok/s
Llama 3.2 3B 3B Q8_0 5 GB Runs ~143 tok/s
Phi-3 Mini 3.8B 3.8B Q8_0 5.8 GB Runs ~124 tok/s
Phi-4 Mini 3.8B 3.8B Q4_K_M 4.5 GB Runs ~159 tok/s
Gemma 3 4B 4B Q4_K_M 5 GB Runs ~143 tok/s
Gemma 3n E4B 4B Q4_K_M 4.5 GB Runs ~159 tok/s
Qwen 3 4B 4B Q4_K_M 4.5 GB Runs ~159 tok/s
DeepSeek R1 7B 7B Q8_0 9 GB Runs ~80 tok/s
Falcon 3 7B 7B Q4_K_M 6.8 GB Runs ~105 tok/s
Mistral 7B 7B Q8_0 9 GB Runs ~80 tok/s
Qwen 2.5 7B 7B Q8_0 9 GB Runs ~80 tok/s
Qwen 2.5 Coder 7B 7B Q8_0 9 GB Runs ~80 tok/s
Qwen 2.5 VL 7B 7B Q4_K_M 7 GB Runs ~102 tok/s
Cogito 8B 8B Q4_K_M 7.5 GB Runs ~96 tok/s
DeepSeek R1 8B 8B Q4_K_M 7.5 GB Runs ~96 tok/s
Llama 3.1 8B 8B Q8_0 10 GB Runs ~72 tok/s
Nemotron 3 Nano 8B 8B Q4_K_M 7.5 GB Runs ~96 tok/s
Qwen 3 8B 8B Q4_K_M 7.5 GB Runs ~96 tok/s
Gemma 2 9B 9B Q8_0 11 GB Runs ~65 tok/s
Falcon 3 10B 10B Q4_K_M 8.5 GB Runs ~84 tok/s
Llama 3.2 Vision 11B 11B Q4_K_M 8.5 GB Runs ~84 tok/s
Gemma 3 12B 12B Q4_K_M 10.5 GB Runs ~68 tok/s
Mistral Nemo 12B 12B Q4_K_M 9.5 GB Runs ~75 tok/s
DeepSeek R1 14B 14B Q4_K_M 9.9 GB Runs ~72 tok/s
Phi-4 14B 14B Q4_K_M 9.9 GB Runs ~72 tok/s
Phi-4 Reasoning 14B 14B Q4_K_M 11 GB Runs ~65 tok/s
Qwen 2.5 14B 14B Q4_K_M 9.9 GB Runs ~72 tok/s
Qwen 2.5 Coder 14B 14B Q4_K_M 12 GB Runs ~60 tok/s
Qwen 3 14B 14B Q4_K_M 12 GB Runs ~60 tok/s
Codestral 22B 22B Q4_K_M 14.7 GB Runs (tight) ~49 tok/s
StarCoder2 15B 15B Q8_0 17 GB CPU Offload ~13 tok/s
Devstral 24B 24B Q4_K_M 17 GB CPU Offload ~13 tok/s
Magistral Small 24B 24B Q4_K_M 17 GB CPU Offload ~13 tok/s
Mistral Small 3.1 24B 24B Q4_K_M 18 GB CPU Offload ~12 tok/s
Gemma 2 27B 27B Q4_K_M 17.7 GB CPU Offload ~12 tok/s
Gemma 3 27B 27B Q4_K_M 20 GB CPU Offload ~11 tok/s
Qwen 3 30B-A3B (MoE) 30B Q4_K_M 22 GB CPU Offload ~10 tok/s
Cogito 32B 32B Q4_K_M 21.5 GB CPU Offload ~10 tok/s
DeepSeek R1 32B 32B Q4_K_M 20.7 GB CPU Offload ~11 tok/s
Qwen 2.5 32B 32B Q4_K_M 20.7 GB CPU Offload ~11 tok/s
Qwen 2.5 Coder 32B 32B Q4_K_M 23 GB CPU Offload ~9 tok/s
Qwen 3 32B 32B Q4_K_M 23 GB CPU Offload ~9 tok/s
QwQ 32B 32B Q4_K_M 21.5 GB CPU Offload ~10 tok/s
Command R 35B 35B Q4_K_M 22.5 GB CPU Offload ~10 tok/s
20 model(s) are too large for this hardware.