Can SmolVLM2 500M Video Instruct run on the RX 7700 XT?
Yes. At 8K context the best fit is F16, using about 1.6 GB of the 11.4 GB usable on the RX 7700 XT. Estimated speed ceiling: ~527 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | Max tok/s (est., 8K) |
|---|---|---|---|
| 2-bit (Q2_K) | 0.8 GB Fits | 1.0 GB Fits | 2270 |
| 3-bit (Q3_K_M) | 0.9 GB Fits | 1.0 GB Fits | 1742 |
| 4-bit (Q4_K_M) | 0.9 GB Fits | 1.1 GB Fits | 1393 |
| 5-bit (Q5_K_M) | 1.0 GB Fits | 1.1 GB Fits | 1195 |
| 6-bit (Q6_K) | 1.0 GB Fits | 1.2 GB Fits | 1038 |
| 8-bit (Q8_0) • | 1.1 GB Fits | 1.2 GB Fits | 989 |
| 16-bit (F16/BF16) • | 1.4 GB Fits | 1.6 GB Fits | 527 |
• real GGUF file size from ggml-org/SmolVLM2-500M-Video-Instruct-GGUF. Speed is a bandwidth ceiling (432 GB/s), not a benchmark. Methodology.
More
SmolVLM2 500M Video Instruct 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 (HuggingFaceTB/SmolVLM2-500M-Video-Instruct), AMD specs. Data as of 2026-11-17.