Llama 3.2 1B Instruct on NVIDIA GeForce RTX 5090
NVIDIA GeForce RTX 5090 runs Llama 3.2 1B Instruct excellently at 300 tok/s at Q8_0. This is a strong pairing.
Model Size
1.24B
Device VRAM
32 GB
Bandwidth
1792 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Llama 3.2 1B Instruct performance at a different quality level on NVIDIA GeForce RTX 5090.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q8_0 | 300 tok/s | 12ms | ✓ Yes | Excellent | estimated |
Notes
Q8_0
1792 GB/s. Maximum possible 1B inference speed.
About Llama 3.2 1B Instruct
Llama 3.2 1B Instruct (1.24B) is a chat, coding model. The smallest Llama model. Runs on integrated GPUs and even CPUs. Useful for basic classification, simple Q&A, and as a draft model for speculative decoding. Limited reasoning capability.
View all Llama 3.2 1B 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
Source: Performance estimates based on model size and device bandwidth (2026-03-15)
Data last updated: 2026-03-15