--- title: TestSprite CLI + QWEN 3.6 (Local LLM) — Zero-Cost... description: A walkthrough of using TestSprite CLI with a local LLM (Qwen/Ornith model via LM Studio) and a local coding agent (Pico coding agent) to run automated software... canonical: https://daily.dev/posts/testsprite-cli-qwen-3-6-local-llm-zero-cost-agentic-software-testing-3f8mlaban twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: TestSprite CLI + QWEN 3.6 (Local LLM) — Zero-Cost Agentic Software Testing | daily.dev og:description: A walkthrough of using TestSprite CLI with a local LLM (Qwen/Ornith model via LM Studio) and a local coding agent (Pico coding agent) to run automated software... og:url: https://daily.dev/posts/testsprite-cli-qwen-3-6-local-llm-zero-cost-agentic-software-testing-3f8mlaban og:image: https://api.daily.dev/og/posts/3F8mlABan.png og:image:alt: TestSprite CLI + QWEN 3.6 (Local LLM) — Zero-Cost Agentic Software Testing 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. # TestSprite CLI + QWEN 3.6 (Local LLM) — Zero-Cost Agentic Software Testing **[Execute Automation](https://daily.dev/sources/executeautomation)** · 11 min read · 0 upvotes · 0 comments ## Summary A walkthrough of using TestSprite CLI with a local LLM (Qwen/Ornith model via LM Studio) and a local coding agent (Pico coding agent) to run automated software tests at zero cost. The setup involves installing TestSprite CLI, configuring it with an API key, and letting the local coding agent orchestrate test execution against a live deployment URL. The demo shows 20 frontend tests running in parallel, completing successfully with roughly 684K input tokens processed entirely on local hardware — no cloud API spend required. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Can I use TestSprite CLI with a local LLM instead of a cloud model like Copilot? Yes, TestSprite CLI can run entirely with a locally hosted LLM such as a Qwen-based Onith model loaded in LM Studio, paired with a coding agent like Pi coding agent. This setup avoids cloud API costs since the model runs on local hardware, though TestSprite still requires a publicly accessible deployment URL (not localhost) to execute the actual tests against. _developers testing local-llm agentic workflows can compare setups and tools on daily.dev._ ### How many tokens does running a full TestSprite test suite with a local coding agent consume? A full run of 20 front-end tests using a local coding agent with TestSprite CLI consumed about 684,000 input tokens and 7,400 output tokens. Because the model runs locally via LM Studio, this token usage costs nothing in API fees, unlike running the same workflow against a cloud-hosted model. _anyone budgeting llm-driven test runs can track token usage patterns like this via daily.dev._ ## Similar posts on daily.dev - [My local LLM can call every tool that Claude can, except it runs on my own hardware](https://daily.dev/posts/my-local-llm-can-call-every-tool-that-claude-can-except-it-runs-on-my-own-hardware-du52dfxnm) · XDA Developers · 2 upvotes · 0 comments - [Using Local Coding Agents](https://daily.dev/posts/using-local-coding-agents-oxctgltkz) · Sebastian Raschka · 2 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#testing](https://daily.dev/tags/testing), [#ai-agents](https://daily.dev/tags/ai-agents), [#lm-studio](https://daily.dev/tags/lm-studio) [View this post on daily.dev](https://daily.dev/posts/testsprite-cli-qwen-3-6-local-llm-zero-cost-agentic-software-testing-3f8mlaban) ```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":"TestSprite CLI + QWEN 3.6 (Local LLM) — Zero-Cost Agentic Software Testing","url":"https://daily.dev/posts/testsprite-cli-qwen-3-6-local-llm-zero-cost-agentic-software-testing-3f8mlaban","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/testsprite-cli-qwen-3-6-local-llm-zero-cost-agentic-software-testing-3f8mlaban"},"datePublished":"2026-08-04T08:13:04.830Z","dateModified":"2026-09-14T08:34:58.596Z","description":"A walkthrough of using TestSprite CLI with a local LLM (Qwen/Ornith model via LM Studio) and a local coding agent (Pico coding agent) to run automated software...","image":"https://i.ytimg.com/vi/kcoiq8W5PlU/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/kcoiq8W5PlU/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Execute Automation","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":"Organization","name":"Execute Automation","logo":"https://media.daily.dev/image/upload/s--Uh-EE9Cf--/f_auto,q_auto/v1780213688/logos/executeautomation?_a=BAMAMiWQ0","url":"https://daily.dev/sources/executeautomation"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/testsprite-cli-qwen-3-6-local-llm-zero-cost-agentic-software-testing-3f8mlaban","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,testing,ai-agents,lm-studio","timeRequired":"PT11M","video":{"@type":"VideoObject","name":"TestSprite CLI + QWEN 3.6 (Local LLM) — Zero-Cost Agentic Software Testing","description":"A walkthrough of using TestSprite CLI with a local LLM (Qwen/Ornith model via LM Studio) and a local coding agent (Pico coding agent) to run automated software...","thumbnailUrl":"https://i.ytimg.com/vi/kcoiq8W5PlU/sddefault.jpg","uploadDate":"2026-08-04T08:13:04.830Z","duration":"PT11M","url":"https://api.daily.dev/r/3F8mlABan","embedUrl":"https://www.youtube.com/embed/kcoiq8W5PlU"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Execute Automation","item":"https://daily.dev/sources/executeautomation"},{"@type":"ListItem","position":3,"name":"TestSprite CLI + QWEN 3.6 (Local LLM) — Zero-Cost Agentic Software Testing"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/testsprite-cli-qwen-3-6-local-llm-zero-cost-agentic-software-testing-3f8mlaban#faq","mainEntity":[{"@type":"Question","name":"Can I use TestSprite CLI with a local LLM instead of a cloud model like Copilot?","acceptedAnswer":{"@type":"Answer","text":"Yes, TestSprite CLI can run entirely with a locally hosted LLM such as a Qwen-based Onith model loaded in LM Studio, paired with a coding agent like Pi coding agent. This setup avoids cloud API costs since the model runs on local hardware, though TestSprite still requires a publicly accessible deployment URL (not localhost) to execute the actual tests against. developers testing local-llm agentic workflows can compare setups and tools on daily.dev."}},{"@type":"Question","name":"How many tokens does running a full TestSprite test suite with a local coding agent consume?","acceptedAnswer":{"@type":"Answer","text":"A full run of 20 front-end tests using a local coding agent with TestSprite CLI consumed about 684,000 input tokens and 7,400 output tokens. Because the model runs locally via LM Studio, this token usage costs nothing in API fees, unlike running the same workflow against a cloud-hosted model. anyone budgeting llm-driven test runs can track token usage patterns like this via daily.dev."}}]} ```