RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Mage VL Cowork run on the RTX 5060?

Yes. At 8K context the best fit is Q8_0, using about 6.2 GB of the 7.6 GB usable on the RTX 5060. Estimated speed ceiling: ~95 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.9 GB Fits3.5 GB Fits6.8 GB Tight20.3 GB No252
3-bit (Q3_K_M)3.4 GB Fits4.0 GB Fits7.3 GB Tight20.8 GB No193
4-bit (Q4_K_M) •3.8 GB Fits4.3 GB Fits7.7 GB No21.2 GB No165
5-bit (Q5_K_M)4.4 GB Fits5.0 GB Fits8.3 GB No21.8 GB No133
6-bit (Q6_K)4.9 GB Fits5.4 GB Fits8.8 GB No22.3 GB No115
8-bit (Q8_0) •5.6 GB Fits6.2 GB Fits9.6 GB No23.1 GB No95
16-bit (F16/BF16) •9.5 GB No10.0 GB No13.4 GB No26.9 GB No—

• real GGUF file size from ggml-org/Mage-VL-Cowork-GGUF. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.

More

Mage VL Cowork on every GPU and Mac · Every model that runs on the RTX 5060 · Other models that fit 8 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (microsoft/Mage-VL-Cowork), NVIDIA specs. Data as of 2026-11-17.