Can Meta Llama Guard 2 8B run on the 2x RTX 3090?
Yes. At 8K context the best fit is F16, using about 16.6 GB of the 45.6 GB usable on the 2x RTX 3090. Estimated speed ceiling: ~58 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | Max tok/s (est., 8K) |
|---|---|---|---|
| 2-bit (Q2_K) • | 4.1 GB Fits | 4.6 GB Fits | 294 |
| 3-bit (Q3_K_M) • | 4.9 GB Fits | 5.4 GB Fits | 233 |
| 4-bit (Q4_K_M) • | 5.7 GB Fits | 6.2 GB Fits | 190 |
| 5-bit (Q5_K_M) • | 6.5 GB Fits | 7.0 GB Fits | 163 |
| 6-bit (Q6_K) • | 7.3 GB Fits | 7.8 GB Fits | 142 |
| 8-bit (Q8_0) • | 9.1 GB Fits | 9.6 GB Fits | 110 |
| 16-bit (F16/BF16) | 16.1 GB Fits | 16.6 GB Fits | 58 |
• real GGUF file size from tybrs/llama-guard-quant. Speed is a bandwidth ceiling (936 GB/s), not a benchmark. Methodology.
More
Meta Llama Guard 2 8B on every GPU and Mac · Every model that runs on the 2x RTX 3090 · Try other settings in the calculator
Data: Hugging Face Hub (meta-llama/Meta-Llama-Guard-2-8B), NVIDIA specs. Data as of 2026-11-17.