AI Model Radar
中文 EN

Llama 4 Scout 17B 16E Instruct

Meta
Model overview

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

Meta's current public Llama 4 Scout 17B 16E instruction-tuned open-weight model.

general LLMreasoningvision-languageagentlong contextchatcode generationlocal inference
CompareCompanyRankingsPublic signals
Representative version

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

CompanyMeta
ReleaseNot disclosed
Release typeModel release
Parameters109B / 17B active
ArchitectureMoE
ContextNot disclosed
Input modalitiestext / image
Output modalitiestext
Tool use / function callingNot disclosed
Structured output / reasoningNot disclosed
Vision / audio / videoConfirmed: Vision; Not shown: Audio, Video
Open weights / LicenseWeights available / Llama 4 Community License
License sourcemeta-llama-4-scout-17b-16e-instruct-current · 2026-07-15
Vendor APINot disclosed
API source pending verification
OpenRouterOpenRouter listed
PricingOpenRouter · 2026-07-15: $0.1 / $0.3
input / output, per 1M tokens
BenchmarkNo reliable public source
Public signals1 activity snapshot
Use casesassistant chat / code generation / local inference / general text tasks
Claim evidenceRelease / model specs / weightsmeta-llama/Llama-4-Scout-17B-16E-Instruct · Hugging FaceLlama-4-Scout-17B-16E-Instruct
OpenRouter

Pricing / context / availability

OpenRouterOpenRouter listed
OpenRouter listingmeta-llama/llama-4-scout
Mapped versionLlama-4-Scout-17B-16E-Instruct
meta-llama-4-scout-17b-16e-instruct-current
PricingOpenRouter · 2026-07-15: $0.1 / $0.3
input / output, per 1M tokens
Context10000000
Speed/LatencyNo reliable public source
Snapshot time2026-07-15T20:11:41.551Z
SourceView source
Public activity counters

Cumulative Hugging Face model-card downloads / likes / spaces

PlatformEntryDownloadsLikesSpacesTimeSource
huggingfacemeta-llama/Llama-4-Scout-17B-16E-Instruct587,3001,3231002026-07-15T20:11:41.551ZView source
Evidence gaps

Public display boundary

Release date not disclosedNo reliable benchmark sourceNo linkable real reviewSpeed/latency not disclosed