How much VRAM does r1-1776 need?

Its published quantizations range from 138.66 GiB to 1250.09 GiB in weights alone, before KV cache and runtime overhead.

r1-1776 on Apple M5 Pro

Can I run r1-1776 on a Apple M5 Pro?

Q: Can I run r1-1776 on a Apple M5 Pro?

No. No published quantization of r1-1776 fits a Apple M5 Pro at any context with q8_0 KV cache.

Not at these settings. No indexed quantization of r1-1776 fits Apple M5 Pro at any context we compute, with q8_0 KV. The smallest shipped quantization is 138.66 GiB in weights alone, against 33.48 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— 48 GB card, 33.48 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◐
BF16	1250.09 GiB	1250.9	1251.0	1251.3	1251.9	1253.0	1255.3
Q8_0	664.30 GiB	665.1	665.2	665.5	666.1	667.2	669.5
Q6_K	512.97 GiB	513.7	513.9	514.2	514.7	515.9	518.2
Q5_K_M	442.75 GiB	443.5	443.7	443.9	444.5	445.7	447.9
Q5_K_S	430.10 GiB	430.9	431.0	431.3	431.9	433.0	435.3
Q4_1	391.10 GiB	391.9	392.0	392.3	392.9	394.0	396.3
Q4_K_M	376.65 GiB	377.4	377.6	377.9	378.4	379.6	381.8
Q4_K_S	353.90 GiB	354.7	354.8	355.1	355.7	356.8	359.1
Q4_0	353.00 GiB	353.8	353.9	354.2	354.8	355.9	358.2
IQ4_NL	352.10 GiB	352.9	353.0	353.3	353.9	355.0	357.3
IQ4_XS	332.60 GiB	333.4	333.5	333.8	334.4	335.5	337.8
Q3_K_L	323.58 GiB	324.4	324.5	324.8	325.4	326.5	328.8
Q3_K_M	297.28 GiB	298.0	298.2	298.5	299.0	300.2	302.5
IQ3_M	272.03 GiB	272.8	272.9	273.2	273.8	274.9	277.2
Q3_K_S	269.23 GiB	270.0	270.1	270.4	271.0	272.1	274.4
IQ3_XS	254.08 GiB	254.8	255.0	255.3	255.8	257.0	259.3
IQ3_XXS	240.22 GiB	241.0	241.1	241.4	242.0	243.1	245.4
Q2_K_L	228.11 GiB	228.9	229.0	229.3	229.9	231.0	233.3
Q2_K	227.27 GiB	228.0	228.2	228.5	229.0	230.2	232.5
IQ2_M	202.50 GiB	203.3	203.4	203.7	204.3	205.4	207.7
IQ2_S	183.47 GiB	184.2	184.4	184.7	185.2	186.4	188.7
IQ2_XS	181.69 GiB	182.5	182.6	182.9	183.5	184.6	186.9
IQ2_XXS	162.45 GiB	163.2	163.4	163.6	164.2	165.4	167.6
IQ1_M	138.66 GiB	139.4	139.6	139.9	140.4	141.6	143.8

●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, this model uses latent attention and allocates no V cache at all, so any formula reading num_key_value_heads overstates its cache by more than an order of magnitude.