picksbycard
August 23, 2026No. 113
Home / Will it run? / Llama 3.3 70B Instruct
Meta · Llama 3.3

Will Llama 3.3 70B Instruct run on my GPU?

70.6B parameters, 131,072-token context, Llama 3.3 Community License. At Q4_K_M the weights come to about 39.5 GiB; add 1.5 GiB for the runtime and you need roughly 41.0 GiB of VRAM before context.

Weights by quant

GiB
Q4_K_M · the everyday quant39.5 GiB
Q8_0 · near-lossless69.7 GiB
FP16 · full weights131.5 GiB
Runtime reserve1.5 GiB

Card by card

0 of 17 fit at Q4
CardVRAMQ4_K_MQ8_0FP16Headroom at Q4
GeForce RTX 5090NVIDIA 32GB OffloadNoNo short by 9.0 GiB
GeForce RTX 3090 (used)NVIDIA · used market 24GB OffloadNoNo short by 17.0 GiB
GeForce RTX 4090 (used)NVIDIA · used market 24GB OffloadNoNo short by 17.0 GiB
Radeon RX 7900 XTXAMD 24GB OffloadNoNo short by 17.0 GiB
GeForce RTX 5060 Ti 16GBNVIDIA 16GB NoNoNo short by 25.0 GiB
GeForce RTX 5070 TiNVIDIA 16GB NoNoNo short by 25.0 GiB
GeForce RTX 5080NVIDIA 16GB NoNoNo short by 25.0 GiB
Radeon RX 7800 XTAMD 16GB NoNoNo short by 25.0 GiB
Radeon RX 9060 XT 16GBAMD 16GB NoNoNo short by 25.0 GiB
Radeon RX 9070AMD 16GB NoNoNo short by 25.0 GiB
Radeon RX 9070 XTAMD 16GB NoNoNo short by 25.0 GiB
Arc B580Intel 12GB NoNoNo short by 29.0 GiB
GeForce RTX 3060 12GB (used)NVIDIA · used market 12GB NoNoNo short by 29.0 GiB
GeForce RTX 4070 SuperNVIDIA · used market 12GB NoNoNo short by 29.0 GiB
GeForce RTX 5070NVIDIA 12GB NoNoNo short by 29.0 GiB
Arc B570Intel 10GB NoNoNo short by 31.0 GiB
GeForce RTX 5060NVIDIA 8GB NoNoNo short by 33.0 GiB

Headroom is what remains for the KV cache after weights and the 1.5 GiB reserve. How far it stretches depends on the architecture: grouped-query models are frugal, older dense models are not. If the table says tight, plan on a shorter context or a lower quant. Parameter count from the model's own card.

The Silicon Note

One short read on the GPU market, most mornings. No spam, one-click out.