OwnRig

Qwen 2.5 14B Instruct on NVIDIA GeForce RTX 3080 10GB

NVIDIA GeForce RTX 3080 10GB can run Qwen 2.5 14B Instruct at 24 tok/s at Q3_K_M, though performance is acceptable. Consider a higher-end GPU for better results.

Model Size

14.77B

Device VRAM

10 GB

Bandwidth

760 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Qwen 2.5 14B Instruct performance at a different quality level on NVIDIA GeForce RTX 3080 10GB.

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q3_K_M24 tok/s260ms✓ YesAcceptableestimated

Notes

Q3_K_M

Q3_K_M fits in 10GB. Tight. Bandwidth helps throughput.

About Qwen 2.5 14B Instruct

Qwen 2.5 14B Instruct (14.77B) is a chat, coding, reasoning, multi-purpose model. Strong general-purpose model with excellent coding and reasoning balance.

View all Qwen 2.5 14B Instruct hardware options →

About NVIDIA GeForce RTX 3080 10GB

NVIDIA GeForce RTX 3080 10GB has 10 GB at 760 GB/s. Street price: $399.

See all models NVIDIA GeForce RTX 3080 10GB can run →

Source: Performance estimates based on model size and device bandwidth (2026-03-15)

Data last updated: 2026-03-15