LLMHardware.io

OpenHands Local Software Agent — Hardware Requirements by Model Size

By Billy G.R. · 2 October 2026

Key facts

Checked
2026-10-02
Author
Billy G.R.

Checked 2026-10-02. Author: Billy G.R. Retail prices move; the hardware catalog stores the Amazon snapshot, not a promise of stock.

Citeable facts

Claim. OpenHands is an open software-agent project: Agent Canvas, a Python SDK, a CLI, and a commercial Cloud. The legacy Docker Local GUI is deprecated.

Method. docs.openhands.dev and github.com/OpenHands/OpenHands, read 2 October 2026.

As of.

Claim. Local 7B is not a stand-in for a frontier coding model. A 7B Q4 is about 6.2 GB and is only for light issues.

Method. 7 × 0.5 × 1.2 + 2 = 6.2. Quality judgment, not a benchmark I ran.

As of.

Claim. A 27–32B Q4 loop, the tier that can attempt SWE-style edits, needs about 18–21 GB.

Method. 27 × 0.6 + 2 = 18.2. 32 × 0.6 + 2 = 21.2. Muse Glimmer Q4 formula is 20 GB.

As of.

Methodology — parameter math, quantization bytes, and the source list.

OpenHands (the project that used to be called OpenDevin, under the All Hands banner) is a software agent: it edits code, runs commands, and can browse. Docs are at docs.openhands.dev. There is also OpenHands Cloud, which is their hosted sandbox. This page is the local install. Cloud needs no VRAM. Local needs a model that fits, and the docs are honest that a strong model is what makes the agent good. A 7B on a laptop is a demo.

Which binary you should actually run

The documentation index I read splits the project. Agent Canvas is the browser client. The Software Agent SDK and Agent Server are the library and the API. The CLI is described as feature-complete and kept stable. The old Local GUI — the Docker app from the former monorepo — is marked deprecated, with a pointer to Agent Canvas. Sandbox Server is a separate community control plane for creating those sandboxes. If a tutorial still starts with the legacy GUI image, it is a historical doc.

The model is not included. You point the agent at Ollama, vLLM, or another OpenAI-compatible endpoint. LM Studio’s local server works as that endpoint when you want a desktop UI for picking the GGUF. Browser tasks can use browser-use; I did not re-confirm the old OpenHands SDK deep link after the docs split, so start from the docs index.

Requirements by what you expect it to finish

I am sorting by task, not by a leaderboard. Formula is the site one. Context for a repo is why the “fits” column is harsher than a chatbot table. Use the VRAM calculator with the slider off the 4K default.

Tier Model What I would ask it to do
12 GB 7B Q4 (6.2 GB) or a tight 14B (10.4 GB) Light issues, a single-file edit. Not a multi-file SWE loop.
24 GB Qwen3.8-27B (18.2 GB), K2-32B (21.2 GB), Muse Glimmer (~20 GB formula, ~17 GB Meta K-quant) The first tier where a coding loop is worth the setup time.
64–128 GB Long context on that 32B, or a large MoE whose total weights fit Repo-wide context plus a browser. Still not “Claude quality” by magic of RAM.

OpenHands Cloud exists because local small models disappoint people. Use Cloud, or Cursor, or Devin, when the outcome matters more than the location of the weights. Use this page when the location is the requirement.

Two machines from the catalog

For the 24 GB tier on Apple Silicon, the Studio M5 Max 36 GB (B0HGKSQMX6, $2,449 on 1 October 2026) leaves a little room past a 32B Q4 for the sandbox. For long context or a large MoE beside the agent, the EVO-X2 128 GB (B0F53MLYQ6, $3,649.99) is the memory buy, with the usual Strix Halo bandwidth limit. A discrete 24 GB card remains the CUDA option; B0BG94PS2F is the RTX 4090 listing already in the catalog.

Mac Studio M5 Max 36 GB on Amazon

ASIN B0HGKSQMX6. Amazon Associates link. The live price is on that page, not locked in here.

GMKtec EVO-X2 128 GB on Amazon

ASIN B0F53MLYQ6. Amazon Associates link. The live price is on that page, not locked in here.

Related guides

Sources

A correction or a hardware question goes to the contact page.