Skip to main contentThe Local Bench

Coding · All Hands AI

OpenHands LM 32B

Hugging Face: all-hands/openhands-lm-32b-v0.1 · checked 2026-10-13

Qwen2.5-Coder-32B fine-tuned for the OpenHands agent.

Datasheet

Maker
All Hands AI
Parameters
32.76 BVerifiedsafetensors.total from the HF API Source
Licence
MITVerified
Access
Public download
Task (HF pipeline)
text-generation
First published on HF
2025-03-26
Last updated on HF
2025-04-16
Weights in memory
66 GB at 16-bit · 20 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build.

Benchmark

37.2%
SWE-bench Verified, % resolved · #2 of 2 scored in this category

Model card, iterative evaluation protocol. Source

The description summarises the model card at https://huggingface.co/all-hands/openhands-lm-32b-v0.1. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.