MetaLlama 3.2 3B Instruct on NVIDIA GeForce RTX 5090
Yes — RTX 5090 runs Llama 3.2 3B Instruct excellently at Q8_0 — 200 tok/s. 32 GB VRAM with plenty of headroom.
Model Size
3.21B
Device VRAM
32 GB
Bandwidth
1792 GB/s
Quantization
Q8_0
Performance by Quantization
OwnRig currently has one published compatibility entry for Llama 3.2 3B Instruct on NVIDIA GeForce RTX 5090 at Q8_0. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q8_0 | 200 tok/s | 20ms | ✓ Yes | Excellent | estimated |
Notes
Q8_0
1792 GB/s bandwidth. Maximum possible 3B speed.
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 5090
NVIDIA GeForce RTX 5090 has 32 GB at 1792 GB/s. Street price: $2,199.
See all models NVIDIA GeForce RTX 5090 can run →Builds with NVIDIA GeForce RTX 5090
Estimate method: Performance estimates based on model size and device bandwidth. Reference hardware source: github.com (2026-03-15)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.