Can Llama Guard 4 12B run on the RX 7900 GRE?
Yes. At 8K context the best fit is Q6_K, using about 11.5 GB of the 15.2 GB usable on the RX 7900 GRE. Estimated speed ceiling: ~59 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 5.7 GB Fits | 6.5 GB Fits | 11.0 GB Fits | 29.0 GB No | 128 |
| 3-bit (Q3_K_M) | 7.0 GB Fits | 7.7 GB Fits | 12.2 GB Fits | 30.2 GB No | 98 |
| 4-bit (Q4_K_M) | 8.4 GB Fits | 9.1 GB Fits | 13.6 GB Fits | 31.6 GB No | 79 |
| 5-bit (Q5_K_M) | 9.5 GB Fits | 10.2 GB Fits | 14.7 GB Tight | 32.7 GB No | 67 |
| 6-bit (Q6_K) | 10.7 GB Fits | 11.5 GB Fits | 16.0 GB No | 34.0 GB No | 59 |
| 8-bit (Q8_0) | 13.4 GB Fits | 14.2 GB Tight | 18.7 GB No | 36.7 GB No | 45 |
| 16-bit (F16/BF16) | 23.9 GB No | 24.6 GB No | 29.1 GB No | 47.1 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (576 GB/s), not a benchmark. Methodology.
More
Llama Guard 4 12B on every GPU and Mac · Every model that runs on the RX 7900 GRE · Other models that fit 16 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (meta-llama/Llama-Guard-4-12B), AMD specs. Data as of 2026-11-17.