TPSTokens Per Second

FastContext-1.0-4B-SFT

Microsoft🇺🇸 United States
active
Compare with other models →
Context window262K tokens

Version History

1.0major

Initial release of FastContext-1.0 repository explorer family with 4B and 30B parameter variants trained via supervised fine-tuning and reinforcement learning.

Coverage

model releaseMicrosoft

Microsoft Releases FastContext-1.0: 4B-Parameter Repository Explorer Cuts Coding Agent Token Use by 60%

Microsoft released FastContext-1.0, a lightweight repository-exploration subagent for LLM coding agents spanning 4B to 30B parameters. The model reduced main-agent token consumption by up to 60% while improving end-to-end resolution rates by up to 5.5% on SWE-bench Pro when integrated with agents like GPT-5.4 and GLM-5.1.

2 min read
microsoftcoding-agentsrepository-search