OwnRig

Qwen 2.5 72B Instruct on NVIDIA GeForce RTX 4060 8GB

NVIDIA GeForce RTX 4060 8GB cannot run Qwen 2.5 72B Instruct at any quantization level. The 8 GB of VRAM is insufficient.

Model Size

72.7B

Device VRAM

8 GB

Bandwidth

272 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Qwen 2.5 72B Instruct performance at a different quality level on NVIDIA GeForce RTX 4060 8GB.

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q2_K✗ OffloadNot Viableestimated

Notes

Q2_K

72B class. Not viable on 8GB.

About Qwen 2.5 72B Instruct

Qwen 2.5 72B Instruct (72.7B) is a chat, coding, ai coding, reasoning, multi-purpose model. Top-tier 72B model, competitive with Llama 3.1 70B. Excellent at coding and structured output. Requires 48GB+ VRAM for usable quantizations.

View all Qwen 2.5 72B Instruct hardware options →

About NVIDIA GeForce RTX 4060 8GB

NVIDIA GeForce RTX 4060 8GB has 8 GB at 272 GB/s. Street price: $289.

See all models NVIDIA GeForce RTX 4060 8GB can run →

Source: 72B model exceeds 8GB (2026-03-15)

Data last updated: 2026-03-01