---
type: "post"
id: "muse-spark-open-is-now-available-on-modal-c28c51"
slug: "muse-spark-open-is-now-available-on-modal-c28c51"
title: "Muse Spark Open is now available on Modal"
description: "Thesis: The practical value of an open model release depends on both access to its weights and a usable serving path."
retrieval_nugget: "Thesis: The practical value of an open model release depends on both access to its weights and a usable serving path."
published_at: "2026-10-15"
updated_at: "2026-10-15"
record_date: "2026-10-15"
date_kind: "published_at"
topics: ["open-models","inference"]
source_urls: ["https://modal.com/blog/meta-muse-spark-open-now-available-on-modal"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:muse-spark-open-is-now-available-on-modal-c28c51"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:633b471706176a2f5eba4118accd6e96b6e49a7eb58d1561defce70fe1753306","reviewed_at":"2026-10-15T23:07:15.668Z","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":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"The practical value of an open model release depends on both access to its weights and a usable serving path.","observed_facts":[{"text":"Modal says Meta released Muse Spark Open weights.","source_urls":["https://modal.com/blog/meta-muse-spark-open-now-available-on-modal"]},{"text":"Modal lists the model as a Shared Endpoint in Auto Endpoints with per-token billing.","source_urls":["https://modal.com/blog/meta-muse-spark-open-now-available-on-modal"]},{"text":"The post reports scores of 76.4 on Terminal-Bench 2.1 with Terminus 2 and 60 on DeepSWE 1.1 with Meta’s preferred harness, using xhigh reasoning effort.","source_urls":["https://modal.com/blog/meta-muse-spark-open-now-available-on-modal"]}],"mechanism":"Users can move from released weights to a hosted inference endpoint without assembling the serving path themselves.","why_now":"The release joins open weights to a concrete managed serving option, so builders can evaluate the model through an existing runtime rather than treating availability as a weights-only event.","implications":["Teams can test the model on their own agentic coding tasks through Modal’s endpoint.","Reported benchmark scores are bounded by the stated harnesses and reasoning setting, and should not be generalized to other configurations."],"evidence_boundary":"The supplied public source is Modal’s announcement; its benchmark figures are attributed to Meta and the post points to the model card for evaluation settings. It does not provide independent replication, latency, cost comparisons, or results on a reader’s own workload.","watch_conditions":["Check whether the model card and subsequent independent evaluations clarify reproducibility, serving performance, and quality across alternative agent harnesses."],"related_records":[],"new_branch_reason":"No prior New Runtime analytical record was supplied for this specific weights-to-hosted-endpoint availability event."}
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/muse-spark-open-is-now-available-on-modal-c28c51/","markdown":"https://newruntime.com/posts/muse-spark-open-is-now-available-on-modal-c28c51.md","json":"https://newruntime.com/posts/muse-spark-open-is-now-available-on-modal-c28c51.json"}
---

# Muse Spark Open is now available on Modal

## Retrieval answer

Thesis: The practical value of an open model release depends on both access to its weights and a usable serving path.

Thesis: The practical value of an open model release depends on both access to its weights and a usable serving path.

Modal reports that Meta released Muse Spark Open weights and that the model is available as a Shared Endpoint in Modal Auto Endpoints, billed per token. The post positions the model for agentic coding and long-horizon work, citing native multimodal understanding, a 1-million-token context window, sequential tool use, and failure recovery. These facts describe the offered model and deployment path; they do not establish that every capability works equally well in every workload.

Mechanism: Users can move from released weights to a hosted inference endpoint without assembling the serving path themselves. The endpoint and billing mode lower the operational steps for trying the model, while the benchmark results offer a bounded reference point rather than a deployment guarantee. Why now: The release joins open weights to a concrete managed serving option, so builders can evaluate the model through an existing runtime rather than treating availability as a weights-only event.

Implication: Teams considering agentic coding systems can test Muse Spark Open within Modal’s endpoint and compare it against their current harness and tasks. Teams can test the model on their own agentic coding tasks through Modal’s endpoint. Modal reports Meta’s scores of 76.4 on Terminal-Bench 2.1 with Terminus 2 and 60 on DeepSWE 1.1 with Meta’s preferred harness, at xhigh reasoning effort. Those setup details matter: the reported scores should not be read as apples-to-apples evidence against other configurations.

Evidence boundary: The supplied public source is Modal’s announcement; its benchmark figures are attributed to Meta and the post points to the model card for evaluation settings. It does not provide independent replication, latency, cost comparisons, or results on a reader’s own workload.

Watch condition: Check whether the model card and subsequent independent evaluations clarify reproducibility, serving performance, and quality across alternative agent harnesses.

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)