Can granite vision 4.1 4b run on the RTX 4060?
Yes. At 8K context the best fit is Q8_0, using about 4.6 GB of the 7.6 GB usable on the RTX 4060. Estimated speed ceiling: ~75 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 2.3 GB Fits | 2.6 GB Fits | 4.5 GB Fits | 12.0 GB No | 181 |
| 3-bit (Q3_K_M) | 2.7 GB Fits | 3.0 GB Fits | 4.9 GB Fits | 12.4 GB No | 139 |
| 4-bit (Q4_K_M) • | 2.9 GB Fits | 3.2 GB Fits | 5.0 GB Fits | 12.5 GB No | 130 |
| 5-bit (Q5_K_M) • | 3.2 GB Fits | 3.5 GB Fits | 5.4 GB Fits | 12.9 GB No | 112 |
| 6-bit (Q6_K) • | 3.5 GB Fits | 3.8 GB Fits | 5.7 GB Fits | 13.2 GB No | 97 |
| 8-bit (Q8_0) • | 4.3 GB Fits | 4.6 GB Fits | 6.5 GB Fits | 14.0 GB No | 75 |
| 16-bit (F16/BF16) • | 7.2 GB Tight | 7.6 GB Tight | 9.4 GB No | 16.9 GB No | 40 |
• real GGUF file size from ibm-granite/granite-vision-4.1-4b-GGUF. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.
More
granite vision 4.1 4b on every GPU and Mac · Every model that runs on the RTX 4060 · Other models that fit 8 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (ibm-granite/granite-vision-4.1-4b), NVIDIA specs. Data as of 2026-11-17.