Can Llama 3.2 3B run on the RX 7900 XTX?
Yes. At 8K context the best fit is F16, using about 7.5 GB of the 22.8 GB usable on the RX 7900 XTX. Estimated speed ceiling: ~149 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) • | 2.5 GB Fits | 2.9 GB Fits | 5.5 GB Fits | 16.0 GB Fits | 643 |
| 3-bit (Q3_K_M) • | 2.8 GB Fits | 3.2 GB Fits | 5.9 GB Fits | 16.4 GB Fits | 517 |
| 4-bit (Q4_K_M) • | 3.2 GB Fits | 3.6 GB Fits | 6.2 GB Fits | 16.7 GB Fits | 428 |
| 5-bit (Q5_K_M) • | 3.5 GB Fits | 3.9 GB Fits | 6.6 GB Fits | 17.1 GB Fits | 370 |
| 6-bit (Q6_K) • | 3.8 GB Fits | 4.3 GB Fits | 6.9 GB Fits | 17.4 GB Fits | 324 |
| 8-bit (Q8_0) • | 4.7 GB Fits | 5.1 GB Fits | 7.7 GB Fits | 18.2 GB Fits | 250 |
| 16-bit (F16/BF16) | 7.1 GB Fits | 7.5 GB Fits | 10.1 GB Fits | 20.6 GB Tight | 149 |
• real GGUF file size from QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.
More
Llama 3.2 3B on every GPU and Mac · Every model that runs on the RX 7900 XTX · Other models that fit 24 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (meta-llama/Llama-3.2-3B), AMD specs. Data as of 2026-11-17.