---
type: "post"
id: "meta-s-muse-spark-open-now-available-in-831a6b"
slug: "meta-s-muse-spark-open-now-available-in-831a6b"
title: "Meta’s Muse Spark Open now available in Amazon SageMaker JumpStart"
description: "Thesis: For this deployment, model availability becomes operationally meaningful when a team can place the endpoint in an account it controls and choose a serving configuration."
retrieval_nugget: "Thesis: For this deployment, model availability becomes operationally meaningful when a team can place the endpoint in an account it controls and choose a serving configuration."
published_at: "2026-10-16"
updated_at: "2026-10-16"
record_date: "2026-10-16"
date_kind: "published_at"
topics: ["open-models","inference"]
source_urls: ["https://aws.amazon.com/blogs/machine-learning/metas-muse-spark-open-now-available-in-amazon-sagemaker-jumpstart"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:meta-s-muse-spark-open-now-available-in-831a6b"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:4e8cf8c17f9a56c066bf64fb6158d0e2e05a920b666b64cd5c3d20ce0d57074c","reviewed_at":"2026-10-16T04:04:01.495Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":1,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"For this deployment, model availability becomes operationally meaningful when a team can place the endpoint in an account it controls and choose a serving configuration.","observed_facts":[{"text":"AWS says Muse Spark Open is available through SageMaker JumpStart and can be deployed as an endpoint in the customer’s AWS account.","source_urls":["https://aws.amazon.com/blogs/machine-learning/metas-muse-spark-open-now-available-in-amazon-sagemaker-jumpstart"]},{"text":"JumpStart offers BF16 and NVFP4 variants; AWS lists ml.p6-b300.48xlarge for BF16 and ml.p5e.48xlarge for NVFP4.","source_urls":["https://aws.amazon.com/blogs/machine-learning/metas-muse-spark-open-now-available-in-amazon-sagemaker-jumpstart"]},{"text":"AWS lists a one-million-token context window and launch availability in US East (N. Virginia) and US East (Ohio).","source_urls":["https://aws.amazon.com/blogs/machine-learning/metas-muse-spark-open-now-available-in-amazon-sagemaker-jumpstart"]}],"mechanism":"JumpStart offers two variants, BF16 and NVFP4, with AWS specifying ml.p6-b300.48xlarge for BF16 and ml.p5e.48xlarge for NVFP4.","why_now":"AWS has made this model available through its managed deployment hub, converting an open-weight model into an option teams can evaluate through an existing cloud workflow.","implications":["Teams can evaluate the model in an AWS endpoint while configuring account-level deployment choices, but the source does not establish comparative coding quality, total operating cost, or production performance."],"evidence_boundary":"These are claims and deployment details in AWS’s announcement and walkthrough; they are not independent evaluations.","watch_conditions":["Check whether access expands beyond the two named US East regions and whether teams publish workload-specific quality and cost results."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied for this specific SageMaker deployment, so it begins a distinct analytical record."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/meta-s-muse-spark-open-now-available-in-831a6b/","markdown":"https://newruntime.com/posts/meta-s-muse-spark-open-now-available-in-831a6b.md","json":"https://newruntime.com/posts/meta-s-muse-spark-open-now-available-in-831a6b.json"}
---

# Meta’s Muse Spark Open now available in Amazon SageMaker JumpStart

## Retrieval answer

Thesis: For this deployment, model availability becomes operationally meaningful when a team can place the endpoint in an account it controls and choose a serving configuration.

Thesis: For this deployment, model availability becomes operationally meaningful when a team can place the endpoint in an account it controls and choose a serving configuration. AWS reports that Muse Spark Open is available through SageMaker JumpStart and can be deployed to a SageMaker AI endpoint in the customer’s AWS account.

Mechanism: JumpStart offers two variants, BF16 and NVFP4, with AWS specifying ml.p6-b300.48xlarge for BF16 and ml.p5e.48xlarge for NVFP4. The source says the model has 816 billion total parameters, 42 billion active per token, and a one-million-token context window. Why now: AWS has made this model available through its managed deployment hub, converting an open-weight model into an option teams can evaluate through an existing cloud workflow.

First implication: Teams can evaluate the model in an AWS endpoint while configuring account-level deployment choices, but the source does not establish comparative coding quality, total operating cost, or production performance. Evidence boundary: These are claims and deployment details in AWS’s announcement and walkthrough; they are not independent evaluations. First watch condition: Check whether access expands beyond the two named US East regions and whether teams publish workload-specific quality and cost results. Endpoint billing continues while it runs, even when idle, and the required instance quotas matter to adoption. This starts a distinct analytical record because no prior New Runtime record was supplied for this specific SageMaker deployment.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Open Models](https://newruntime.com/topics/open-models.md): Explore the open-models topic hub.
- topic hub: [Inference](https://newruntime.com/topics/inference.md): Explore the inference topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)