Can You Run Qwen2.5 7B served? Every GPU, Tested

Qwen2.5 7B served needs roughly 20GB of VRAM at our tested precision. A model that doesn't fit doesn't run slowly, it doesn't run. Here's every card from our bench, sorted by measured speed.

Weights: Qwen/Qwen2.5-7B

GPUs that run Qwen2.5 7B served (9)

GPUSpeedVRAMBasis
NVIDIA B2005799.1 serve tok/s192GB✓ Measured
NVIDIA H2004394.8 serve tok/s141GB✓ Measured
NVIDIA H100 80GB HBM33601.1 serve tok/s80GB✓ Measured
NVIDIA RTX PRO 6000 Blackwell Workstation Edition2282.8 serve tok/s96GB✓ Measured
NVIDIA A100 80GB SXM42187.2 serve tok/s80GB✓ Measured
NVIDIA A100 40GB SXM41769.6 serve tok/s40GBEst.
NVIDIA L40S1406.8 serve tok/s48GB✓ Measured
NVIDIA A10G858.7 serve tok/s24GB✓ Measured
NVIDIA L4469.9 serve tok/s24GB✓ Measured

GPUs it won't fit on (1)

These cards' VRAM is below the requirement at tested precision, published as data, not hidden.

GPUVRAM
NVIDIA T416GB

Quick answers

How much VRAM does Qwen2.5 7B served need?

Qwen2.5 7B served needs roughly 20GB of VRAM at our tested precision. 9 of the GPUs on our bench run it; 1 don't have the VRAM for it.

What is the fastest GPU for Qwen2.5 7B served?

NVIDIA B200 is the fastest card we've measured running Qwen2.5 7B served, at 5799.1 serve tok/s.

What is the cheapest GPU that can run Qwen2.5 7B served?

NVIDIA L4 ($2,500 MSRP) is the cheapest card on our bench that runs Qwen2.5 7B served, at 469.9 serve tok/s.

← All models · AI GPU rankings · How we benchmark