RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM 1.7B run on the RX 7700 XT?

Yes. At 8K context the best fit is F16, using about 5.2 GB of the 11.4 GB usable on the RX 7700 XT. Estimated speed ceiling: ~126 tokens/sec.

Memory by quant and context

QuantMax tok/s (est., 8K)
2-bit (Q2_K) •640
3-bit (Q3_K_M) •502
4-bit (Q4_K_M) •409
5-bit (Q5_K_M) •353
6-bit (Q6_K) •307
8-bit (Q8_0) •237
16-bit (F16/BF16) •126

• real GGUF file size from mradermacher/SmolLM-1.7B-GGUF. Speed is a bandwidth ceiling (432 GB/s), not a benchmark. Methodology.

More

SmolLM 1.7B 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/SmolLM-1.7B), AMD specs. Data as of 2026-11-17.