Headless Thrones

Meta · Official-source model record

Muse Spark Open 816B A42B

Muse Spark · Version meta-models/Muse-Spark-Open-816B-A42B

AvailableChecked Oct 23, 2026
Editorial (1) ↓Download model brief (.md)

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 Muse Spark Open 816B A42B

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

Which Muse Spark Open 816B A42B does this page describe?

Muse Spark Open 816B A42B is a model record from Meta in the Muse Spark family. Source

The recorded model identifier or checkpoint is meta-models/Muse-Spark-Open-816B-A42B. Use that exact identifier when checking documentation or a provider listing. Source

How can you access Muse Spark Open 816B A42B?

The catalog documents Open weights access for Muse Spark Open 816B A42B. 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 Muse Spark Open 816B A42B's context and output limits?

The documented context window is 1,048,576 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 can Muse Spark Open 816B A42B receive and generate?

Documented inputs: text, image, audio, and video. 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 Muse Spark Open 816B A42B?

The recorded license label is Muse Model 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 distinguishes Muse Spark Open 816B A42B?

These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results.

Architecture and active parameters
Meta describes an 816-billion-parameter mixture-of-experts model with about 42 billion active parameters per token. Total and active counts are different; neither is an independent memory benchmark. Source
Hosting route
This open checkpoint is not a Meta Model API model. It is intended for self-hosting or access through a separate serving provider. Source
Hardware planning
Meta estimates about 1.65 TB for BF16 weights and about 537 GB for NVFP4 weights. Its examples use eight GPUs for BF16 or four Blackwell GPUs for NVFP4; runtime memory and compatibility require separate planning. Source

Keep the exact version in view

Other Muse Spark models from Meta.

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

Muse Spark 1.1

API · 1,048,576 context tokens

Muse Spark 1.2

API · 1,048,576 context tokens

Muse Spark 1.3

API · 1,048,576 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
Muse SparkSource ↗
Version
meta-models/Muse-Spark-Open-816B-A42BSource ↗
Availability
AvailableSource ↗
Access
Open weightsSource ↗
Inputs
Text · Image · Audio · VideoSource ↗
Outputs
TextSource ↗
Context window
1,048,576 tokensSource ↗
Maximum input
Not documented
Maximum output
Not documented
Knowledge cutoff
Not documented
Training-data cutoff
Not documented
Training completed
Not documented
Release date
Not documented
License
Muse Model LicenseSource ↗
Input price / 1M tokens
Not documented
Output price / 1M tokens
Not documented

Read this with the numbers.

Hosted through third-party partners; not assumed to be a native Meta API model. Custom license details require separate review.

Model identifiers and aliases 1
  • meta-models/Muse-Spark-Open-816B-A42B-NVFP4

Follow the evidence

Official sources.

  1. muse spark open — official Meta documentation ↗dev.meta.ai
  2. models — official Meta documentation ↗dev.meta.ai

From the Headless Thrones newsroom

Editorial about Muse Spark Open 816B A42B

1 published article linked to this exact model. Newest first.

Models

Muse Spark Open and Beam: what shipped, what the licenses allow, and what it takes to run them

Two large open-weight models arrived a day apart. Beam is Apache 2.0; Meta's Muse Spark Open carries branding and revenue conditions. Benchmarks so far are the vendors' own.

By Headless Thrones · AI models reporter · AI author

Your starting point

Muse Spark Open 816B A42B

Meta · Open weights

Browse all models ↗
Inputs
Text · Image · Audio · VideoSource ↗
Outputs
TextSource ↗
Context window
1,048,576 tokensSource ↗
Knowledge cutoff
Not documented

A place to begin comparing

6 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.

Baichuan

Baichuan-Omni-1d5

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

Baichuan

Baichuan-Omni-1d5-Base

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

OpenBMB

MiniCPM-o-2_6

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

OpenBMB

MiniCPM-o-4_5

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

Qwen

Qwen2.5-Omni-3B

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

Qwen

Qwen2.5-Omni-7B

Text + Image + Audio + Video 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 ↗