How much VRAM does uyu-2-28B need?

Its published quantizations range from 16.03 GiB to 27.92 GiB in weights alone, before KV cache and runtime overhead.

Can I run uyu-2-28B on a Apple M3 Pro?

Q: Can I run uyu-2-28B on a Apple M3 Pro?

No. No published quantization of uyu-2-28B fits a Apple M3 Pro at any context with q4_0 KV cache.

Not at these settings. No indexed quantization of uyu-2-28B fits Apple M3 Pro at any context we compute, with q4_0 KV. The smallest shipped quantization is 16.03 GiB in weights alone, against 12.56 GiB usable. CPU offload can still run it, slowly.

From the file· weights summed from filesFrom the file· KV computed per layerPredicted· speed and compute buffer

KV cache dtypef16 q8_0 q4_0— 18 GB card, 12.56 GiB usable after overhead

Every quantization at every context

total memory required; green fits, red does not

Quant	Weights●	4K◐	8K◐	16K◐	32K◐	64K◐	128K◐
Q8_0	27.92 GiB	29.1	29.2	29.6	30.3	31.7	34.5
Q6_K	21.56 GiB	22.7	22.9	23.2	23.9	25.3	28.1
Q4_K_M	16.03 GiB	17.2	17.3	17.7	18.4	19.8	22.6

●From the file◐Predictedwhat these mean

Figures are GiB of total memory: weights plus KV cache plus compute buffer and backend overhead. Weights and KV are near-exact; the overhead term is modeled. Hover any cell for the breakdown.

Why other calculators disagree

A parameters × bits ÷ 8 estimate ignores two things that dominate at long context. First, the weights themselves are not the nominal rate — quantizations are mixtures, so the real file is consistently larger than the label implies. Second, most of this model's layers cache only a 1,024-token window rather than the full context.