How much VRAM to run Llama 3.3 70B?

About 51 GB atQ4_K_M with an 8K context — fits a A100 80GB. Full breakdown below, or check your exact hardware.

Llama 3.3 70B VRAM by quantisation

QuantisationWeightsTotal (8K ctx)Fits on
Q4_K_M43.1 GB51.3 GBA100 80GB, RTX PRO 6000 Blackwell
Q5_K_M50.3 GB59.2 GBA100 80GB, RTX PRO 6000 Blackwell
Q6_K57.9 GB67.6 GBA100 80GB, RTX PRO 6000 Blackwell
Q8_075.2 GB86.7 GBRTX PRO 6000 Blackwell, Apple Silicon 128GB unified
FP16 / BF16141.2 GB159.3 GBApple Silicon 256GB unified, Apple Silicon 512GB unified

Check your hardware

About Llama 3.3 70B

Llama 3.3 70B is Meta's 70.6B-parameter model released in December 2024, with a 128K-token context window. It uses a classic dense-attention design whose KV cache grows linearly with context: its KV cache is about 2.7 GB at an 8K context, 42.9 GB at 128K, and 42.9 GB at the full 128K window (FP16 cache).

For most people Q4_K_M is the sweet spot — the most popular quality/size trade-off — while Q8 is near-lossless if you have the memory. Totals above include the KV cache and a realistic framework overhead, so they are what you should expect to see in practice rather than just the download size. Weight sizes are calibrated against real GGUF files — see themethodology.

Frequently asked questions

How much VRAM does Llama 3.3 70B need?

At Q4_K_M with an 8K context, Llama 3.3 70B needs about 51 GB (weights 43 GB + KV cache + overhead). The smallest common hardware that fits is a A100 80GB.

Can an RTX 4090 (24GB) run Llama 3.3 70B?

Not fully in VRAM. Llama 3.3 70B needs about 51 GB even at Q4_K_M, so a 24 GB card would have to offload layers to system RAM at a large speed penalty.

Can a Mac run Llama 3.3 70B?

Yes — Apple Silicon with 96 GB of unified memory or more (macOS lets the GPU use ~75% of it, ~72 GB) runs Llama 3.3 70B at Q4_K_M.

Related

VRAM calculator for any model ·Token counter

Last updated 2026-08-03. Architecture figures from the model's published config.json; see themethodology.