---
type: "raw_signal"
id: "focusing-on-post-training-81ffee"
slug: "focusing-on-post-training-81ffee"
title: "Sebastian Raschka uses Fireworks’ Ember-1 as a case study for post-training an existing open-weight LLM"
description: "Sebastian Raschka uses Fireworks’ Ember-1 as a case study for post-training an existing open-weight LLM rather than repeating costly frontier-scale pretraining."
retrieval_nugget: "Sebastian Raschka uses Fireworks’ Ember-1 as a case study for post-training an existing open-weight LLM rather than repeating costly frontier-scale pretraining."
observed_at: "2026-09-28"
record_date: "2026-09-28"
date_kind: "observed_at"
why_it_matters: "Source: https://sebastianraschka.com/blog/2026/focusing-on-llm-post-training.html"
novelty: "notable"
verification_level: "source-linked"
signal_type: "research"
source_platform: "sebastianraschka.com"
topics: []
entities: []
related_patterns: []
source_url: "https://sebastianraschka.com/blog/2026/focusing-on-llm-post-training.html"
source_urls: ["https://sebastianraschka.com/blog/2026/focusing-on-llm-post-training.html"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:focusing-on-post-training-81ffee"
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/signals/focusing-on-post-training-81ffee/","markdown":"https://newruntime.com/signals/focusing-on-post-training-81ffee.md","json":"https://newruntime.com/signals/focusing-on-post-training-81ffee.json"}
---

# Sebastian Raschka uses Fireworks’ Ember-1 as a case study for post-training an existing open-weight LLM

## Retrieval answer

Sebastian Raschka uses Fireworks’ Ember-1 as a case study for post-training an existing open-weight LLM rather than repeating costly frontier-scale pretraining.

Sebastian Raschka uses Fireworks’ Ember-1 as a case study for post-training an existing open-weight LLM rather than repeating costly frontier-scale pretraining. The article reports Fireworks’ claim that Ember-1, built from Kimi K3, uses roughly 40% fewer tokens while maintaining comparable quality across its evaluations. Raschka attributes the efficiency direction to training for shorter reasoning traces, while explicitly noting that the underlying recipe remains undisclosed.

Source: https://sebastianraschka.com/blog/2026/focusing-on-llm-post-training.html

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`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- 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)