Can FastVLM 0.5B run on the RX 7600?
Yes. At 8K context the best fit is F16, using about 2.2 GB of the 7.6 GB usable on the RX 7600. Estimated speed ceiling: ~190 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 1.0 GB Fits | 1.0 GB Fits | 1.3 GB Fits | 1012 |
| 3-bit (Q3_K_M) | 1.1 GB Fits | 1.1 GB Fits | 1.4 GB Fits | 777 |
| 4-bit (Q4_K_M) | 1.2 GB Fits | 1.2 GB Fits | 1.5 GB Fits | 621 |
| 5-bit (Q5_K_M) | 1.2 GB Fits | 1.3 GB Fits | 1.6 GB Fits | 533 |
| 6-bit (Q6_K) | 1.3 GB Fits | 1.4 GB Fits | 1.6 GB Fits | 463 |
| 8-bit (Q8_0) | 1.5 GB Fits | 1.5 GB Fits | 1.8 GB Fits | 357 |
| 16-bit (F16/BF16) | 2.2 GB Fits | 2.2 GB Fits | 2.5 GB Fits | 190 |
• real GGUF file size. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.
More
FastVLM 0.5B on every GPU and Mac · Every model that runs on the RX 7600 · Other models that fit 8 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (apple/FastVLM-0.5B), AMD specs. Data as of 2026-11-17.