Ctrl K
Back to models

Meta

Llama 4 Scout

  • Released
  • Gated weights
  • Llama 4 Community License Agreement
Compare
Intelligence Index

Standard setting

6.5#78 of 83measured models
Measured · Artificial Analysis v4.3.2
API price from
$0.18 in / $0.59 out / 1M tokOpenRouter · Novita · BF16
Context window
10M tok

Performance profile

ReasoningRank #85 of 107
58.7%
GPQA Diamond
CodingRank #90 of 94
21.3%
SciCode
Cost efficiencyRank #33 of 67
57.5pts / $
Intelligence ÷ eval cost

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
Llama 4 Scout
Cost per task (USD) · log scale
Llama 4 ScoutStandard
Intelligence Index
6.5
Cost / task
$0.1122
Evaluation time
22.2s

Pricing & access

API route
OpenRouter · Novita · BF16API
Tier & contextStandard

USD per 1M tokens

Input
$0.18
Output
$0.59

Run locally

GGUF
Context
Estimated memory

~70.7 GiB

RAM + VRAM

Estimate assumptions

One text chat at the selected context, with a 16-bit cache and app allowance. Operating system and image processing are extra; optimized caches can use less.

96 GiB RAMwithout GPU offload

Memory budgetOne text chat
Weights
62.9 GiB
Context cache
1.5 GiB16-bit cache
App allowance
6.3 GiB
Download
67.5 GB2 files · keep together+1.7 GB for images (opens in a new tab)
Disk space
~82 GBIncludes image file
Available software
Ollama (opens in a new tab)LM Studio (opens in a new tab)Jan (opens in a new tab)KoboldCpp (opens in a new tab)llama.cpp (opens in a new tab)
Get GGUF (opens in a new tab)
Set up in Ollama · Q4_K_M · 8K context

Save the following as Modelfile. The context matches the estimate above.

FROM hf.co/lmstudio-community/Llama-4-Scout-17B-16E-Instruct-GGUF:Q4_K_M
PARAMETER num_ctx 8192

Then run these commands in your terminal:

ollama create llmcurrent-local -f Modelfile
ollama run llmcurrent-local

Ollama import instructions (opens in a new tab) · For LM Studio or Jan, open the app’s model search, enter lmstudio-community/Llama-4-Scout-17B-16E-Instruct-GGUF, choose Q4_K_M, and set context to 8,192 tokens in the app’s model settings. Software links above open each app’s setup guide.

Images need extra memoryvLLM setup (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Llama 4 Scout · Standard#124 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 120Ministral 3 8BStandard4.3%
  6. 121Nova PremierStandard4.2%
  7. 122Command AStandard4.0%
  8. 123Granite 4.0 H SmallStandard3.8%
  9. 124Llama 4 ScoutStandard3.8%
  10. 125Phi-4Standard3.8%
  11. 126Llama 3.3 Instruct 70BStandard3.6%

Peers use their best measured result on this benchmark.

Alternatives

Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.