Can FastVLM 0.5B run on the RTX 3060 Ti?
Yes. At 8K context the best fit is F16, using about 2.2 GB of the 7.6 GB usable on the RTX 3060 Ti. Estimated speed ceiling: ~295 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 | 1574 |
| 3-bit (Q3_K_M) | 1.1 GB Fits | 1.1 GB Fits | 1.4 GB Fits | 1208 |
| 4-bit (Q4_K_M) | 1.2 GB Fits | 1.2 GB Fits | 1.5 GB Fits | 966 |
| 5-bit (Q5_K_M) | 1.2 GB Fits | 1.3 GB Fits | 1.6 GB Fits | 829 |
| 6-bit (Q6_K) | 1.3 GB Fits | 1.4 GB Fits | 1.6 GB Fits | 720 |
| 8-bit (Q8_0) | 1.5 GB Fits | 1.5 GB Fits | 1.8 GB Fits | 556 |
| 16-bit (F16/BF16) | 2.2 GB Fits | 2.2 GB Fits | 2.5 GB Fits | 295 |
• real GGUF file size. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.
More
FastVLM 0.5B on every GPU and Mac · Every model that runs on the RTX 3060 Ti · Other models that fit 8 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (apple/FastVLM-0.5B), NVIDIA specs. Data as of 2026-11-17.