---
type: "post"
id: "train-muse-glimmer-for-free-our-recipe-for-4f4f83"
slug: "train-muse-glimmer-for-free-our-recipe-for-4f4f83"
title: "Train Muse Glimmer for free: Our recipe for out-betting Jev"
description: "Fireworks AI is offering supervised fine-tuning for Muse Glimmer 30B at no charge through November 30 as the first offer in its Free Weights Club."
retrieval_nugget: "Fireworks AI is offering supervised fine-tuning for Muse Glimmer 30B at no charge through November 30 as the first offer in its Free Weights Club."
published_at: "2026-10-22"
updated_at: "2026-10-22"
record_date: "2026-10-22"
date_kind: "published_at"
topics: ["models"]
entities: ["Fireworks AI","Muse Glimmer 30B","Jev","Kalshi","Free Weights Club","Serverless Training API"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Fireworks reports a Muse Glimmer 30B fine-tuning experiment: tuned Glimmer reached 58.3% prediction accuracy versus Jev’s 47.1%, with a historical $1,000 backtest ending at $1,071, and free SFT through November 30."
prior_refs: ["memory:da8bf4bb-9d2d-8dfe-ab91-4f638a84bae7"]
source_url: "https://fireworks.ai/blog/train-muse-glimmer-for-free"
source_urls: ["https://fireworks.ai/blog/train-muse-glimmer-for-free"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:train-muse-glimmer-for-free-our-recipe-for-4f4f83"
status: "published"
visuals: []
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/train-muse-glimmer-for-free-our-recipe-for-4f4f83/","markdown":"https://newruntime.com/posts/train-muse-glimmer-for-free-our-recipe-for-4f4f83.md","json":"https://newruntime.com/posts/train-muse-glimmer-for-free-our-recipe-for-4f4f83.json"}
---

# Train Muse Glimmer for free: Our recipe for out-betting Jev

## Retrieval answer

Fireworks AI is offering supervised fine-tuning for Muse Glimmer 30B at no charge through November 30 as the first offer in its Free Weights Club.

Fireworks AI is offering supervised fine-tuning for Muse Glimmer 30B at no charge through November 30 as the first offer in its Free Weights Club. The company points users to a Kalshi cookbook and offers both Managed Training and a Serverless Training API.

Fireworks trained a LoRA adapter in one pass over 20,051 historical Kalshi questions from 6,461 events, using K-way cross-entropy over each question's answer choices. It reports 64.8% accuracy on its full evaluation set, versus 56.4% for base Glimmer and 45.9% for Jev. On 113 topic families excluded from training and calibration, tuned Glimmer reached 58.3%, compared with 53.2% and 47.1%.

The company separately calibrated the tuned model's confidence. At predictions of at least 80% probability, it reports 86.8% accuracy, while 14.4% of the full test set and 6.1% of unseen-topic questions met that threshold. Its historical backtest turned a hypothetical $1,000 into $1,071 after modeled fees. The source does not establish independently replicated results, real-world trading performance, or an equivalent comparison: base Glimmer received neither task-specific training nor confidence calibration.

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: [Models](https://newruntime.com/topics/models.md): Explore the models 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)