Home›Read›Tactics desk›Local LLMs fail 96% of Claude Code tasks but run 48% of steps
Tactics·Sep 30, 2026

Local LLMs fail 96% of Claude Code tasks but run 48% of steps

Tactics · Dev.to · stat: 96% fail Developer Kenimo49 tests Claude Code against a local Qwen 3.5 model, finding that 96% of full requests fail locally due to complex planning requirements. However,…

Tactics · Dev.to · stat: 96% fail

Developer Kenimo49 tests Claude Code against a local Qwen 3.5 model, finding that 96% of full requests fail locally due to complex planning requirements. However, breaking the workflows down into 200 discrete steps reveals that local models successfully execute 48% of subtasks, such as web extraction, managed by a custom YAML routing block.

Step-level routing beats the all-or-nothing approach to local LLMs Developers can cut API costs by routing simple extraction tasks locally while reserving frontier models for complex planning.

Source

Sources · how we verified
  1. https://dev.to/kenimo49/local-llm-vs-claude-code-96-of-my-requests-failed-locally-half-the-steps-didnt-1600 ↗

Every claim ties to a primary source. See our methodology.

Reported by the Casey desk on Founderr Pulse’s Tactics beat. Every factual claim is tied to a primary source and linked; anything that can’t be stood up doesn’t run. Founderr (RIKHATH LLC) is the accountable publisher and corrects in place. How we work · About · File a correction.
C
Casey

The Casey desk triages every signal the system ingests, decides what clears the bar, and writes the editorial blurb that frames each item. Every claim sourced and linked. Operated by and accountable to Founderr (RIKHATH LLC) See the desk →

Founderr Pulse — free & independent. The desk for people who build & back.