Llama 3.3 70B VRAM Requirements

Llama 3.3 70B at a glance

Made by

Meta, United States

Released

November 26, 2024

Parameters

70.5B

Context window

128K tokens

License

Llama 3.3 Community License

On Hugging Face

3.1K likes, 342K downloads last month (opens in a new tab)

Runs with

vLLM, SGLang, llama.cpp (Ollama, LM Studio), MLX (Mac) · vLLM recipe (opens in a new tab)

Checked against

KV cache matches the GGUF header of unsloth/Llama-3.3-70B-Instruct-GGUF (opens in a new tab) (what llama.cpp allocates), October 10, 2026

VRAM by precision and context length

Weights plus the KV cache of one request (BF16 cache), in GiB. Add 1 to 3 GiB for the inference engine itself.

Llama 3.3 70B GGUF files

Exact size of each quantization in unsloth/Llama-3.3-70B-Instruct-GGUF (opens in a new tab), and the smallest GPU that runs it with llama.cpp, Ollama or LM Studio and an 8K-token context.

Read every day from Hugging Face. Split files are added together; vision projectors are left out.

How many GPUs to run Llama 3.3 70B

Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.

Cheapest way to run Llama 3.3 70B today

For each GPU: the fewest cards that fit Llama 3.3 70B with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-10-10).

On-demand prices from RunPod, Vast.ai, Verda and Azure, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.

KV cache: how memory grows with context

Architecture: 80 layers · GQA, 8 KV heads × 128. Every layer keeps keys and values for every token (grouped-query attention), so the cache grows linearly with context.

Llama 3.3 70B VRAM badge

For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/llama-3-3-70b.json.

[![Llama 3.3 70B VRAM](https://studiotvai.com/badge/llama-3-3-70b.svg)](https://studiotvai.com/vram-requirements/llama-3-3-70b)

Other models

Same family (dense): Llama 3.1 8B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.1 405B

All models: Llama 3.1 8B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.1 405B · Qwen3.5 4B · Qwen3.5 9B · Qwen3.8 27B · Qwen3.6 35B-A3B · Qwen3.5 122B-A10B · Qwen3.8-Flash-Next · LFM2.5 8B-A1B · LFM2 24B-A2B · Gemma 4 12B · Gemma 4 31B · Gemma 4 26B-A4B · gpt-oss 20B · gpt-oss 120B · Llama 4 Scout 17B-16E · Llama 4 Maverick 17B-128E · Kolibri-1 · Nemotron 3 Nano 30B-A3B · Nemotron 3 Super 120B-A12B · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Kimi K3 · Mistral Large 4 · Qwen3-Coder-Next 80B-A3B · Qwen3-Coder 30B-A3B · Qwen3-Coder 480B-A35B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Ornith 1.5 35B-A3B · Ornith 1.5 9B · Atria Dawn Preview · Intern S2 397B · Clef · Clef Flash · D1 3B · Humanizer · JEV 27B VL · Mellum2.1 12B-A2.5B · LightOnOCR-3 4B · Spark-X2.5 4B · Agnes-3.0-Qwen

Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.