Llama 4 Scout 17B-16E VRAM Requirements

Llama 4 Scout 17B-16E at a glance

Made by

Meta, United States

Released

April 2, 2025

Parameters

108.6B, 17B active

Context window

10M tokens

License

Llama 4 Community License

On Hugging Face

1.4K likes, 166K 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)

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 4 Scout 17B-16E GGUF files

Exact size of each quantization in unsloth/Llama-4-Scout-17B-16E-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 4 Scout 17B-16E

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 4 Scout 17B-16E today

For each GPU: the fewest cards that fit Llama 4 Scout 17B-16E 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: MoE 16 experts · 36 chunked-attention layers (8192-token chunks, 8 KV × 128) · 12 global layers. Its KV cache is 2.3× smaller than if every layer used full attention, because most layers only keep a short window of recent tokens. Only 17B parameters are active per token, but all 109B must sit in memory: VRAM depends on the total, speed on the active part.

Llama 4 Scout 17B-16E 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-4-scout.json.

[![Llama 4 Scout 17B-16E VRAM](https://studiotvai.com/badge/llama-4-scout.svg)](https://studiotvai.com/vram-requirements/llama-4-scout)

Other models

Same family (sliding-window attention): Gemma 4 12B · Gemma 4 31B · Gemma 4 26B-A4B · gpt-oss 20B · gpt-oss 120B · Llama 4 Maverick 17B-128E · Kolibri-1 · Humanizer · Mellum2.1 12B-A2.5B · Spark-X2.5 4B

All models: Llama 3.1 8B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · 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 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.