Fitting WhisperX large-v3 + a 24B LLM on one 3090: a reproducible context-capping recipe
The article discusses a method for fitting WhisperX large-v3 and a 24B LLM on a single RTX 3090 GPU. It details the technical steps taken to avoid out-of-memory errors while maintaining performance. The author provides a reproducible recipe, including measurements and configurations for effective resource management.
- ▪The setup includes a 24GB RTX 3090, WhisperX large-v3 for speech-to-text, and a Devstral Small 24B LLM for email triage.
- ▪By capping the context window to 8192 tokens, the total memory usage was reduced to 21.9GB, preventing out-of-memory errors.
- ▪The author created a dashboard to monitor VRAM usage per service, which helped identify and resolve contention issues.
DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | DEV.to (Top) |
| Canonical URL | https://dev.to/sikamikanikobg/fitting-whisperx-large-v3-a-24b-llm-on-one-3090-a-reproducible-context-capping-recipe-22g0 |
| Publication time | Wed, 03 Jun 2026 03:35:14 +0000 |
| Retrieval time | 2026-06-03T03:41:54.046Z |
| Last seen | 2026-06-03T03:41:54.046Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | CiOclZfWZqbX |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 1410108) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Arsen Apostolov Posted on Jun 3 Fitting WhisperX large-v3 + a 24B LLM on one 3090: a reproducible context-capping recipe #homelab #ollama #localllm #devops This is the technical, reproducible version of a fix I shipped on my own homelab. If you want the narrative version, that's on Medium. This one is the recipe: the measurements, the math, the Modelfile, and the exact prompt I gave Claude Code to generate it. Copy-paste friendly.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
