OwnRig

Llama 3.2 3B Instruct on NVIDIA GeForce RTX 5080

NVIDIA GeForce RTX 5080 runs Llama 3.2 3B Instruct excellently at 160 tok/s at Q8_0. This is a strong pairing.

Model Size

3.21B

Device VRAM

16 GB

Bandwidth

960 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Llama 3.2 3B Instruct performance at a different quality level on NVIDIA GeForce RTX 5080.

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q8_0160 tok/s28ms✓ YesExcellentestimated

Notes

Q8_0

960 GB/s bandwidth. Near-instant 3B inference.

About Llama 3.2 3B Instruct

Llama 3.2 3B Instruct (3.21B) is a chat, coding, ai coding, reasoning model. Ultra-lightweight model that runs on virtually any GPU. Surprisingly capable for its size — good at summarization, simple coding tasks, and quick chat. The default choice when speed matters more than depth.

View all Llama 3.2 3B Instruct hardware options →

About NVIDIA GeForce RTX 5080

NVIDIA GeForce RTX 5080 has 16 GB at 960 GB/s. Street price: $1,099.

See all models NVIDIA GeForce RTX 5080 can run →

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

Data last updated: 2026-03-15