OpenModelsHQ

Llama-4-Scout-17B-16E-Instruct

MetaVisionDenseLlama 4 license

Llama-4-Scout-17B-16E-Instruct is an open-weight vision and language model from Meta with 109B parameters. At 4-bit it needs about 77.4 GB of memory, so the smallest current device that fits it is the RTX PRO 6000 Blackwell.

Overview

Estimated memory at 4-bit
77.4GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
109B
Dense
Context window
Unknown
Not in the model config
Cheapest API, blended / 1M
$0.12
₹11 · DeepInfra · 3:1 input to output
All Meta API prices

Key information

Lab
Meta
Released
2 Apr 2025
Parameters
109B
Type
Vision and language
Context
Unknown
HF downloads, 30 days
110,339
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
Llama-4-Scout-17B-16E-Instruct needs about 77.4 GB at 4-bit, 136.8 GB at 8-bit and 258.1 GB at 16-bit. At 4-bit it fits DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q477.4 GB
Q8136.8 GB
BF16258.1 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 77.4 GBToo big 215%RTX PRO 6000 Blackwell96 GB memory
8-bit (Q8)≈ 136.8 GBToo big 380%Mac Studio M5 Ultra (256GB)256 GB memory
16-bit (BF16)≈ 258.1 GBToo big 717%RubinAnnounced288 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

Start with the MLX files, built for Apple Silicon.

mlx-community/Llama-4-Scout-17B-16E-Instruct-4bitCheck your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

unsloth/Llama-4-Scout-17B-16E-Instruct-GGUFFind compatible hardware

Through an API

DeepInfra (fp8) is the cheapest provider we found.

$0.08 / $0.24

Input / output per 1M tokens
₹7.54 / ₹23 at ₹94.29 per $1

Blended: $0.12 (₹11) per 1M. Ranked by a 3:1 mix of input and output tokens.

MLX on Apple SiliconView repository
mlx_vlm.generate --model mlx-community/Llama-4-Scout-17B-16E-Instruct-4bit \
  --prompt "Describe this image." --image image.jpg
GGUF with llama.cppView repository
llama-cli -hf unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of MLX or llama.cpp. We have not run them; check each repository for available files.

Hosted API 2

USD and INR per million tokensAll Meta API prices
Precision
DeepInfraCheapest$0.12₹11$0.08₹7.54$0.24₹23327,680FP8
Google$0.3625₹34$0.25₹24$0.70₹661,310,720Not listed
View on OpenRouterEndpoint sourceSorted by the blended price: 3 parts input to 1 part output. Context limits differ by provider.

INR at ₹94.29 per $1. Prices fetched 14 Nov 2026.

More about this model

Frequently asked questions

How much memory does Llama-4-Scout-17B-16E-Instruct need? At an 8k context, about 77.4 GB at 4-bit, 136.8 GB at 8-bit and 258.1 GB at 16-bit (BF16). A longer context needs more.

Can I run Llama-4-Scout-17B-16E-Instruct on a Mac? The smallest current Mac that fits the 4-bit estimate of 77.4 GB is the Mac Studio M5 Max (128GB). An MLX build is available: mlx-community/Llama-4-Scout-17B-16E-Instruct-4bit.

Does the full context fit? We do not have a context length for this model. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? The cheapest provider we found is DeepInfra, at $0.08 per 1M input tokens and $0.24 per 1M output tokens (₹7.54 and ₹23 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

License in plain English

Llama 4 license. Meta's community license for Llama. It allows commercial use with conditions, including an acceptable use policy and extra terms for very large services. This summary is not legal advice.

Read the license on the model card

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources