RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can FastVLM 0.5B run on the RX 9070 XT?

Yes. At 8K context the best fit is F16, using about 2.2 GB of the 15.2 GB usable on the RX 9070 XT. Estimated speed ceiling: ~422 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.0 GB Fits1.0 GB Fits1.3 GB Fits2249
3-bit (Q3_K_M)1.1 GB Fits1.1 GB Fits1.4 GB Fits1726
4-bit (Q4_K_M)1.2 GB Fits1.2 GB Fits1.5 GB Fits1380
5-bit (Q5_K_M)1.2 GB Fits1.3 GB Fits1.6 GB Fits1184
6-bit (Q6_K)1.3 GB Fits1.4 GB Fits1.6 GB Fits1029
8-bit (Q8_0)1.5 GB Fits1.5 GB Fits1.8 GB Fits794
16-bit (F16/BF16)2.2 GB Fits2.2 GB Fits2.5 GB Fits422

• real GGUF file size. Speed is a bandwidth ceiling (640 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

FastVLM 0.5B on every GPU and Mac · Every model that runs on the RX 9070 XT · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (apple/FastVLM-0.5B), AMD specs. Model data last checked 2026-11-17; refreshed hourly.