RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolVLM 500M Instruct run on the RX 9070?

Yes. At 8K context the best fit is F16, using about 1.6 GB of the 15.2 GB usable on the RX 9070. Estimated speed ceiling: ~780 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)0.8 GB Fits1.0 GB Fits3363
3-bit (Q3_K_M)0.9 GB Fits1.0 GB Fits2580
4-bit (Q4_K_M)0.9 GB Fits1.1 GB Fits2063
5-bit (Q5_K_M)1.0 GB Fits1.1 GB Fits1770
6-bit (Q6_K)1.0 GB Fits1.2 GB Fits1538
8-bit (Q8_0) •1.1 GB Fits1.2 GB Fits1465
16-bit (F16/BF16) •1.4 GB Fits1.6 GB Fits780

• real GGUF file size from ggml-org/SmolVLM-500M-Instruct-GGUF. Speed is a bandwidth ceiling (640 GB/s), not a benchmark. Methodology.

More

SmolVLM 500M Instruct on every GPU and Mac · Every model that runs on the RX 9070 · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (HuggingFaceTB/SmolVLM-500M-Instruct), AMD specs. Data as of 2026-11-17.