OwnRig

Qwen 2.5 Coder 32B Instruct on NVIDIA GeForce RTX 4070 Ti Super

NVIDIA GeForce RTX 4070 Ti Super can run Qwen 2.5 Coder 32B Instruct at 16 tok/s at Q3_K_M, though performance is acceptable. Consider a higher-end GPU for better results.

Model Size

32.5B

Device VRAM

16 GB

Bandwidth

672 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Qwen 2.5 Coder 32B Instruct performance at a different quality level on NVIDIA GeForce RTX 4070 Ti Super.

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q3_K_M16 tok/s600ms✓ YesAcceptableestimated

Notes

Q3_K_M

Same VRAM constraint as 4060 Ti but 2.3x bandwidth yields better speed. Still Q3 quality compromise.

About Qwen 2.5 Coder 32B Instruct

Qwen 2.5 Coder 32B Instruct (32.5B) is a coding, ai coding, ai building model. The coding model that defines the builder workflow. Matches GPT-4 on HumanEval. This is what Cursor and Continue.dev users run locally when they want to eliminate API dependency. Apache 2.0 license. The cornerstone of the 'Full AI Builder' profile.

View all Qwen 2.5 Coder 32B Instruct hardware options →

About NVIDIA GeForce RTX 4070 Ti Super

NVIDIA GeForce RTX 4070 Ti Super has 16 GB at 672 GB/s. Street price: $779.

See all models NVIDIA GeForce RTX 4070 Ti Super can run →

Source: Extrapolated from bandwidth scaling (2026-01-15)

Data last updated: 2026-03-01