Can Llama 3.2 1B run on the RX 7800 XT?
Yes. At 8K context the best fit is F16, using about 3.2 GB of the 15.2 GB usable on the RX 7800 XT. Estimated speed ceiling: ~252 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) • | 1.4 GB Fits | 1.5 GB Fits | 2.3 GB Fits | 5.3 GB Fits | 935 |
| 3-bit (Q3_K_M) • | 1.5 GB Fits | 1.6 GB Fits | 2.4 GB Fits | 5.4 GB Fits | 776 |
| 4-bit (Q4_K_M) • | 1.7 GB Fits | 1.8 GB Fits | 2.5 GB Fits | 5.5 GB Fits | 653 |
| 5-bit (Q5_K_M) • | 1.8 GB Fits | 1.9 GB Fits | 2.7 GB Fits | 5.7 GB Fits | 571 |
| 6-bit (Q6_K) • | 1.9 GB Fits | 2.0 GB Fits | 2.8 GB Fits | 5.8 GB Fits | 504 |
| 8-bit (Q8_0) • | 2.3 GB Fits | 2.4 GB Fits | 3.1 GB Fits | 6.1 GB Fits | 390 |
| 16-bit (F16/BF16) | 3.1 GB Fits | 3.2 GB Fits | 3.9 GB Fits | 6.9 GB Fits | 252 |
• real GGUF file size from QuantFactory/Dolphin3.0-Llama3.2-1B-GGUF. Speed is a bandwidth ceiling (624 GB/s), not a benchmark. Methodology.
More
Llama 3.2 1B on every GPU and Mac · Every model that runs on the RX 7800 XT · Other models that fit 16 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (meta-llama/Llama-3.2-1B), AMD specs. Model data last checked 2026-11-17; refreshed hourly.