Can Llama 3.2 11B Vision run on the RX 7700 XT?
Yes. At 8K context the best fit is Q6_K, using about 10.0 GB of the 11.4 GB usable on the RX 7700 XT. Estimated speed ceiling: ~50 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) | 5.0 GB Fits | 5.6 GB Fits | 9.4 GB Fits | 24.4 GB No | 108 |
| 3-bit (Q3_K_M) | 6.1 GB Fits | 6.7 GB Fits | 10.5 GB Tight | 25.5 GB No | 83 |
| 4-bit (Q4_K_M) | 7.3 GB Fits | 8.0 GB Fits | 11.7 GB No | 26.7 GB No | 66 |
| 5-bit (Q5_K_M) | 8.3 GB Fits | 9.0 GB Fits | 12.7 GB No | 27.7 GB No | 57 |
| 6-bit (Q6_K) | 9.4 GB Fits | 10.0 GB Fits | 13.8 GB No | 28.8 GB No | 50 |
| 8-bit (Q8_0) | 11.8 GB No | 12.4 GB No | 16.2 GB No | 31.2 GB No | — |
| 16-bit (F16/BF16) | 21.1 GB No | 21.7 GB No | 25.5 GB No | 40.5 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (432 GB/s), not a benchmark. Methodology.
More
Llama 3.2 11B Vision on every GPU and Mac · Every model that runs on the RX 7700 XT · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (meta-llama/Llama-3.2-11B-Vision), AMD specs. Data as of 2026-11-17.