OwnRig

Qwen 2.5 Coder 32B Instruct on NVIDIA GeForce RTX 4080 Super

NVIDIA GeForce RTX 4080 Super can run Qwen 2.5 Coder 32B Instruct at 18 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

736 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 4080 Super.

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q3_K_M18 tok/s550ms✓ YesAcceptableestimated

Notes

Q3_K_M

16GB VRAM requires Q3 for 32B. Usable for code completion with 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 4080 Super

NVIDIA GeForce RTX 4080 Super has 16 GB at 736 GB/s. Street price: $979.

See all models NVIDIA GeForce RTX 4080 Super can run →

Source: Community benchmarks and estimated performance (2026-03-01)

Data last updated: 2026-03-01