← All GPUs
GeForce RTX 4080
NVIDIA · Consumer GPU · 2022
Check Latest Price
$1,199 MSRP
Check Price on Amazon →
We earn a commission from qualifying purchases · Prices may vary
Performance Benchmarks
LLM Inference all sourced rows →
| Model | Metric | Value | Source |
|---|---|---|---|
|
Qwen3-8B
Q4_K_XL Token generation: 16K context, batch 1, Ubuntu 24.04, on-hardware lab measurement |
tokens per second |
77.9
tok/s
llama.cpp llama-bench, CUDA 12.8 · 2025-12-09
|
Estimate Hardware Corner LLM GPU Rankings ↗ |
Full Specifications
Vram gb
16 GB
Vram type
GDDR6X
Memory bus
256 bit
Memory bandwidth gbps
716.8 GB/s
Tdp watts
320 W
Cuda cores
9728
Pcie interface
PCIe 4.0 x16
Architecture
Ada Lovelace
Related GPUs
Guides & Tools
CompareAIHardware.com participates in the Amazon Associates program. As an Amazon Associate, we earn from qualifying purchases.