RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 4 Maverick 17B 128E Instruct run on the RTX 5060?

No. Even at 2-bit with 8K context, Llama 4 Maverick 17B 128E Instruct needs about 138 GB, more than the 7.6 GB usable on the RTX 5060.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •137 GB No138 GB No142 GB No160 GB No—
3-bit (Q3_K_M) •179 GB No180 GB No185 GB No203 GB No—
4-bit (Q4_K_M) •228 GB No228 GB No233 GB No251 GB No—
5-bit (Q5_K_M) •266 GB No267 GB No272 GB No290 GB No—
6-bit (Q6_K) •308 GB No308 GB No313 GB No331 GB No—
8-bit (Q8_0) •398 GB No399 GB No403 GB No421 GB No—
16-bit (F16/BF16) •748 GB No749 GB No753 GB No771 GB No—

• real GGUF file size from unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.

Hardware that does fit it

Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB

More

Llama 4 Maverick 17B 128E Instruct 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 (meta-llama/Llama-4-Maverick-17B-128E-Instruct), NVIDIA specs. Data as of 2026-11-17.