Headless Thrones

Meta · Official-source model record

Llama 4 Maverick 17B 128E Instruct

Llama 4 · Version meta-llama/Llama-4-Maverick-17B-128E-Instruct

AvailableChecked Oct 23, 2026
Editorial (0) ↓Download model brief (.md)
Find its building ↗

Publisher-sourced inventory. Specifications come from official documentation and model cards. “Not documented” means we have no verified value. This inventory is separate from our editorial reviews.

Coverage & sources ↗

Current catalog answers

What to know about Llama 4 Maverick 17B 128E Instruct

AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.

Which Llama 4 Maverick 17B 128E Instruct does this page describe?

Llama 4 Maverick 17B 128E Instruct is a model record from Meta in the Llama 4 family. Source

The recorded model identifier or checkpoint is meta-llama/Llama-4-Maverick-17B-128E-Instruct. Use that exact identifier when checking documentation or a provider listing. Source

How can you access Llama 4 Maverick 17B 128E Instruct?

The catalog documents Open weights access for Llama 4 Maverick 17B 128E Instruct. Source

As of the catalog check, this version was listed as available. Source

Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement.

What are Llama 4 Maverick 17B 128E Instruct's context and output limits?

The documented context window is 1,000,000 tokens. Source

A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance.

Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.

What dates are documented for Llama 4 Maverick 17B 128E Instruct?

Knowledge cutoff: August 2024. Source This labels the documented knowledge boundary; it is not a promise that every earlier fact is known or correct.

Training-data cutoff: August 2024. Source This describes the reported data boundary, not the day training finished. The source labels this “Pretraining data cutoff.”

Release date: April 5, 2025. Source This is a release milestone, not a knowledge or training cutoff. The source labels this “Model Release Date.”

Retrieval or web tools can supply newer information at run time. That does not change the model's recorded training or knowledge dates, and this record does not establish that a particular endpoint includes those tools.

What can Llama 4 Maverick 17B 128E Instruct receive and generate?

Documented inputs: text and image. Source

Documented outputs: text. Source

Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.

What license is recorded for Llama 4 Maverick 17B 128E Instruct?

The recorded license label is Llama 4 Community License. Source

Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.

What is documented about the Llama 4 Maverick 17B 128E Instruct checkpoint?

This evidence refers to meta-llama/Llama-4-Maverick-17B-128E-Instruct at recorded revision 73d14711bcc77c16df3470856949c3764056b617, checked October 23, 2026. Repository metadata

Safetensors metadata records 401,583,781,376 stored parameters. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. Repository metadata

Recorded architecture class: Llama4ForConditionalGeneration. Repository metadata

Repository task tag: image-text-to-text. A task tag identifies a distribution category; it does not measure performance on that task. Repository metadata

Listed library: transformers. Check that library's version and model support before loading the weights. Repository metadata

Repository language labels: ar, de, en, es, fr, hi, id, it, pt, th, tl, and vi. These labels are not independent evaluations of language quality. Repository metadata

Repository access gate: manual. This records the repository's gate setting when checked; licensing and use terms still apply. Repository metadata

Read the retrieved model card for setup and qualifications. Model card

Keep the exact version in view

Other Llama 4 models from Meta.

These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.

Llama 4 Scout 17B 16E

Open weights · 10,000,000 context tokens

The documented record

Specifications, with their sources.

A missing value remains unknown. Input limits, output limits and the total context window are separate measurements.

Publisher
MetaSource ↗
Family
Llama 4Source ↗
Version
meta-llama/Llama-4-Maverick-17B-128E-InstructSource ↗
Availability
AvailableSource ↗
Access
Open weightsSource ↗
Inputs
Text · ImageSource ↗
Outputs
TextSource ↗
Context window
1,000,000 tokensSource ↗
Maximum input
Not documented
Maximum output
Not documented
Knowledge cutoff
Aug 2024Knowledge cutoff · month precisionSource ↗
Training-data cutoff
Aug 2024Pretraining data cutoff · month precisionSource ↗
Training completed
Not documented
Release date
Apr 5, 2025Model Release Date · day precisionSource ↗
License
Llama 4 Community LicenseSource ↗
Input price / 1M tokens
Not documented
Output price / 1M tokens
Not documented

Read this with the numbers.

Publisher repository evidence (2026-10-23): Publisher task label: image-text-to-text. Published architecture metadata: Llama4ForConditionalGeneration. Repository library label: transformers. Model-card language labels: ar, de, en, es, fr, hi, id, it, pt, th, tl, vi; these labels are not evaluated proficiency scores. Published safetensors metadata counts 401,583,781,376 stored parameters; this is not an active-parameter count for mixture-of-experts models. Repository access metadata is manual; access gating does not establish license permissions.

Model identifiers and aliases 0

No additional identifier has been verified.

Follow the evidence

Official sources.

  1. MODEL_CARD.md ↗github.com
  2. Llama 4 Maverick 17B 128E Instruct official reference ↗huggingface.co
  3. Llama 4 Maverick 17B 128E Instruct: official publisher repository metadata ↗huggingface.co
  4. Llama 4 Maverick 17B 128E Instruct: publisher model card at revision 73d14711bcc7 ↗huggingface.co

From the Headless Thrones newsroom

Editorial about Llama 4 Maverick 17B 128E Instruct

No published articles are linked to this exact model yet. New coverage will appear here as it is published.

Your starting point

Llama 4 Maverick 17B 128E Instruct

Meta · Open weights

Browse all models ↗
Inputs
Text · ImageSource ↗
Outputs
TextSource ↗
Context window
1,000,000 tokensSource ↗
Knowledge cutoff
Aug 2024Knowledge cutoff · month precisionSource ↗

A place to begin comparing

242 models to consider.

Matches must share an access route, support every documented input type of your starting model, and return text. When both publish a context limit in the same field, the candidate must fall between half and twice that limit. Unknown or differently defined limits remain as broader matches, after verified near-context matches. Within each group, recent documented releases appear first. These criteria do not establish equal quality. The full current inventory is considered.

MiniMax

MiniMax-M3.1-Flash

Text + Image input; text output · Shared access: Open weights · Documented context within ½–2×

Mistral AI

Mistral Large 4

Text + Image input; text output · Shared access: Open weights · Documented context within ½–2×

MiniMax

MiniMax-M3

Text + Image input; text output · Shared access: Open weights · Documented context within ½–2×

Meta

Llama 4 Maverick 17B 128E

Text + Image input; text output · Shared access: Open weights · Documented context within ½–2×

DeepSeek

DeepSeek-V4.1-Flash-1017

Text + Image input; text output · Shared access: Open weights · Documented context within ½–2×

Meta

Muse Spark Open 816B A42B

Text + Image input; text output · Shared access: Open weights · Documented context within ½–2×

Moonshot AI

Kimi-K3

Text + Image input; text output · Shared access: Open weights · Documented context within ½–2×

StepFun

Step-5-Preview

Text + Image input; text output · Shared access: Open weights · Documented context within ½–2×

Z.ai

GLM-5.3-Flash

Text + Image input; text output · Shared access: Open weights · Documented context within ½–2×

NVIDIA

Nemotron-3.5-Parse

Text + Image input; text output · Shared access: Open weights · Capacity match not established

A record you can follow

The source belongs beside the fact.

Official sources

Model records cite the developer’s documentation, release notes and model cards. A listing alone is not a tested service or a recommendation.

Dates mean different things

Knowledge cutoff, training-data cutoff, training completion and release date are separate fields. A model’s name or repository upload date does not establish any of them.

Limits need context

Some publishers use rounded K/M token figures. Deployment, reasoning settings and regional access can change usable limits. Read the source before choosing.

Coverage and last check

Independent editorial model library assembled from primary vendor documentation and official publisher model cards. This is a dated, auditable inventory of the sources reviewed, not a claim to every model worldwide. First-party language-model inventory for OpenAI, Anthropic, Google Gemini/Gemma, xAI, Meta and Reflection. Includes vendor-listed legacy/retired identities with explicit statuses; official pretrained and instruction-tuned checkpoints remain distinct. Excludes embeddings, moderation/guard models, image/audio/video-only generation, community fine-tunes, speculative draft helpers, format/runtime/quantization duplicates, and PaliGemma dataset-specific benchmark fine-tunes. Availability means documented vendor API or downloadable official weights, not guaranteed account eligibility. Unknown specifications and dates remain null. Rounded K/M limits preserve vendor granularity; exact integers are used only where documented. No OpenRouter facts are used. Primary-source inventory of language-capable models from Alibaba/Qwen, DeepSeek, Moonshot, MiniMax, Z.ai, ByteDance Seed, Tencent, Baidu, Xiaomi, StepFun, 01.AI, Shanghai AI Laboratory, Baichuan and OpenBMB. Includes full reachable official public weight inventories plus documented hosted API models and explicit retirements. Embeddings, reward/classifier/router/tokenizer/draft-head components, standalone OCR/document converters and image/video/audio-only generators are excluded; multimodal language models retained. Official packaging variants are folded into aliases where a canonical listing was identifiable; remaining research/base/SFT variants retain exact identities. Not a guarantee every historical/private/regional model is available. Unknown specifications remain null; K/M API display quantities use decimal normalization where explicitly noted, rather than implying verified exact serving ceilings. Model-name dates and repository creation timestamps are never used as release/training dates. Open weights does not mean unrestricted or OSI-open-source licensing. Some model-card bodies were unreachable; their public inventory metadata is retained and disclosed. Official Mistral, Cohere, AI21, NVIDIA Nemotron, Microsoft Phi/MAI, Amazon Nova, IBM Granite, AllenAI OLMo/Molmo, TII Falcon, Nous Research, Arcee and Essential AI model inventory checked 2026-10-23. Includes base, instruction, reasoning, coding and text-producing multimodal models, including legacy API versions. Excludes embeddings/rerankers/reward and safety classifiers, image/audio/video-only generation, robotics-only models, duplicate quantization/runtime packages, adapters, intermediate checkpoint experiments, and third-party mirrors. Arcee coverage focuses on its named product families rather than exploratory merge repositories. Repository listing means listed, not independently verified API availability. K/M figures are nominal decimal normalizations when the source supplies shorthand; deployment-specific exact token limits may differ. Unverified values remain null. This is a source-backed inventory, not a complete claim-level independent editorial review. Supplemental official Liquid AI, Reka and Inception generative language catalog. Excludes media-only generators and decision/classification-only models. No assumed training dates.

Catalog edition updated . Source links are provided on each model record.

View the full coverage report and discovery sources ↗