GAIR/OpenSWE-72B
TEXT GENERATIONConcurrency Cost:4Model Size:72.7BQuant:FP8Ctx Length:32kPublished:Mar 15, 2026License:qwenArchitecture:Transformer0.0K Warm

OpenSWE-72B, developed by GAIR, is a 72.7 billion parameter language model with a 32768 token context length, specifically fine-tuned for Software Engineering (SWE) tasks. It is trained on OpenSWE, the largest fully transparent framework for SWE agent training, comprising 45,320 executable Docker environments. This model achieves 66.0% on SWE-bench Verified, establishing a new state-of-the-art among SFT-based methods in the Qwen2.5 series, and shows significant out-of-domain improvements in math and science benchmarks without degrading factual recall.

Loading preview...

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p