<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/how-to-connect-local-ai-models-to-bruno-ai-ollama-and-lm-studio-jeo8mycpq" -->

---
title: How to Connect Local AI Models to Bruno AI: Ollama and...
description: A step-by-step guide walks through connecting local AI models to Bruno API client's AI features using Ollama or LM Studio, both of which expose an...
canonical: https://daily.dev/posts/how-to-connect-local-ai-models-to-bruno-ai-ollama-and-lm-studio-jeo8mycpq
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: How to Connect Local AI Models to Bruno AI: Ollama and LM Studio | daily.dev
og:description: A step-by-step guide walks through connecting local AI models to Bruno API client's AI features using Ollama or LM Studio, both of which expose an...
og:url: https://daily.dev/posts/how-to-connect-local-ai-models-to-bruno-ai-ollama-and-lm-studio-jeo8mycpq
og:image: https://api.daily.dev/og/posts/JeO8mYCPq.png
og:image:alt: How to Connect Local AI Models to Bruno AI: Ollama and LM Studio
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# How to Connect Local AI Models to Bruno AI: Ollama and LM Studio

**[Bruno Blog](https://daily.dev/sources/usebruno)** · [@devgancode](https://daily.dev/devgancode) · 14 min read · 0 upvotes · 0 comments

## Summary

A step-by-step guide walks through connecting local AI models to Bruno API client's AI features using Ollama or LM Studio, both of which expose an OpenAI-compatible API. It covers what open-weight models are, how to pick a model size for your hardware, installation and setup for both tools, and how to wire the resulting endpoint into Bruno's Preferences under OpenAI-Compatible Endpoints. It also covers picking a default model, tuning autocomplete trigger modes, leaving Bruno's redaction defaults on, using AI for generating tests, docs, and scripts, prompting tips for smaller models, and a troubleshooting table for common connection and model-ID errors.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://blog.usebruno.com/how-to-connect-local-ai-models-to-bruno-ai>

## Questions this post answers

### How do I connect a local Ollama model to Bruno's AI features?

Add it under Preferences, AI, OpenAI-Compatible Endpoints, not the OpenAI or Anthropic provider rows. Set the base URL to http://localhost:11434/v1, leave the API key blank or use a placeholder, and enter the model ID exactly as shown by ollama list, including the tag, such as qwen2.5-coder:7b. This requires Bruno v4.0.0 or later.

_daily.dev surfaces setup guides like this for developers wiring local models into their tools._

### What causes a 404 or model-not-found error when connecting LM Studio to Bruno?

A 404 usually means the /v1 suffix is missing from the base URL, which should be http://localhost:1234/v1 for LM Studio. A model-not-found error means the model ID doesn't exactly match what's shown in the LM Studio server panel, including any tag or instruct suffix like qwen2.5-coder-7b-instruct.

_developers debugging local AI integrations can find fixes like this on daily.dev._

### What size local AI model should I use for API test generation on a 16GB machine?

A 7B to 8B parameter model, quantized to Q4, is the recommended sweet spot for 16GB of unified memory or VRAM, handling test generation, documentation, scripts, and autocomplete. Code-tuned variants such as Qwen2.5 Coder or DeepSeek Coder produce cleaner JavaScript than general chat models of the same size.

_daily.dev helps developers compare hardware-to-model tradeoffs before committing to a setup._

## Similar posts on daily.dev

- [Local AI Models for Coding 2026: Ollama Setup and Best Models](https://daily.dev/posts/local-ai-models-for-coding-2026-ollama-setup-and-best-models-sohghmj3p) · Alex CloudStar · 1 upvotes · 0 comments
- [I use two apps to run local AI, and each one does something better](https://daily.dev/posts/i-use-two-apps-to-run-local-ai-and-each-one-does-something-better-hv4ilskn4) · XDA Developers · 1 upvotes · 0 comments
- [Run a Local AI Model with Ollama in 15 Minutes](https://daily.dev/posts/run-a-local-ai-model-with-ollama-in-15-minutes-5wx17jt3x) · Machine Learning Mastery · 1 upvotes · 0 comments

---

Tags: [#testing](https://daily.dev/tags/testing), [#local-ai](https://daily.dev/tags/local-ai), [#ollama](https://daily.dev/tags/ollama), [#lm-studio](https://daily.dev/tags/lm-studio)

[View this post on daily.dev](https://daily.dev/posts/how-to-connect-local-ai-models-to-bruno-ai-ollama-and-lm-studio-jeo8mycpq)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"How to Connect Local AI Models to Bruno AI: Ollama and LM Studio","url":"https://daily.dev/posts/how-to-connect-local-ai-models-to-bruno-ai-ollama-and-lm-studio-jeo8mycpq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-to-connect-local-ai-models-to-bruno-ai-ollama-and-lm-studio-jeo8mycpq"},"datePublished":"2026-09-25T11:34:15.199Z","dateModified":"2026-09-26T08:00:10.796Z","description":"A step-by-step guide walks through connecting local AI models to Bruno API client's AI features using Ollama or LM Studio, both of which expose an...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/780efd5a3de2eea4b8452d24e761c0e8?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/780efd5a3de2eea4b8452d24e761c0e8?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Bruno Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Person","name":"Ganesh Patil","url":"https://daily.dev/devgancode","image":"https://media.daily.dev/image/upload/s--YZDsshgS--/f_auto/v1723695126/avatars/avatar_DKBm9qlNzn7jbRNc8qWlD","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":60}},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-to-connect-local-ai-models-to-bruno-ai-ollama-and-lm-studio-jeo8mycpq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"testing,local-ai,ollama,lm-studio","timeRequired":"PT14M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Bruno Blog","item":"https://daily.dev/sources/usebruno"},{"@type":"ListItem","position":3,"name":"How to Connect Local AI Models to Bruno AI: Ollama and LM Studio"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-to-connect-local-ai-models-to-bruno-ai-ollama-and-lm-studio-jeo8mycpq#faq","mainEntity":[{"@type":"Question","name":"How do I connect a local Ollama model to Bruno's AI features?","acceptedAnswer":{"@type":"Answer","text":"Add it under Preferences, AI, OpenAI-Compatible Endpoints, not the OpenAI or Anthropic provider rows. Set the base URL to http://localhost:11434/v1, leave the API key blank or use a placeholder, and enter the model ID exactly as shown by ollama list, including the tag, such as qwen2.5-coder:7b. This requires Bruno v4.0.0 or later. daily.dev surfaces setup guides like this for developers wiring local models into their tools."}},{"@type":"Question","name":"What causes a 404 or model-not-found error when connecting LM Studio to Bruno?","acceptedAnswer":{"@type":"Answer","text":"A 404 usually means the /v1 suffix is missing from the base URL, which should be http://localhost:1234/v1 for LM Studio. A model-not-found error means the model ID doesn't exactly match what's shown in the LM Studio server panel, including any tag or instruct suffix like qwen2.5-coder-7b-instruct. developers debugging local AI integrations can find fixes like this on daily.dev."}},{"@type":"Question","name":"What size local AI model should I use for API test generation on a 16GB machine?","acceptedAnswer":{"@type":"Answer","text":"A 7B to 8B parameter model, quantized to Q4, is the recommended sweet spot for 16GB of unified memory or VRAM, handling test generation, documentation, scripts, and autocomplete. Code-tuned variants such as Qwen2.5 Coder or DeepSeek Coder produce cleaner JavaScript than general chat models of the same size. daily.dev helps developers compare hardware-to-model tradeoffs before committing to a setup."}}]}
```

