What can my computer run?
What model file size fits my computer?
It depends on the file, runtime and your computer's working memory (RAM). As a starting point, keep one model file below 60% of your memory so other apps have room. A size estimate does not prove runtime support, speed or answer quality. Your processor, graphics and other running apps also matter. This page checks this browser, then lists hosted files that fit.
RAM is working memory used while a model runs; disk space stores downloaded files. The numbers below apply a 60% planning allowance to the stated memory size.
The fit rows are calculations from the stated allowance, not measured compatibility results. Use the model finder to inspect current candidates. For a concrete example, open Qwen3-8B file evidence and recorded hashes and its run-readiness record. No successful run is claimed by this estimate.
- 8 GB memory: a file under 4.8 GB.
- 16 GB memory: a file under 9.6 GB.
- 32 GB memory: a file under 19.2 GB.
- 64 GB memory: a file under 38.4 GB.
A smaller file leaves room for other apps. File size does not prove a model will run well. Speed also depends on your processor and graphics.
Updated · Page-copy source revision 8871bab84e1cf80aea1686a944ec335078a6c036 · Source files: apps/web/server.mjs, apps/web/lib/aeo-page.mjs, apps/web/lib/api-status-contract.mjs, apps/web/lib/agent-readable.mjs, apps/web/lib/docs-hub-model.mjs, apps/web/lib/compare-pages.mjs · Full revision record
Key facts
- Fit rows
- Arithmetic from a 60% memory planning rule; not measured compatibility.
- Catalog match
- find-runnable returns hosted candidates; absence means no confirmed pick.
- Graphics
- Not reported in the no-JavaScript first paint on this page.
Evidence you can inspect (plain text)
- The fit table uses a 60% memory planning rule stated on this page.
- /finder lists candidates; find-runnable may return no row when nothing is confirmed.
- Open /artifact/hf-model-qwen-qwen3-8b/files for model exact filenames, availability and any recorded SHA-256.
- Open /evidence/artifacts/hf-model-qwen-qwen3-8b for run-readiness evidence tied to that record; absent receipts stay unmeasured.
- Open /api/artifacts/hf-model-qwen-qwen3-8b/card.md for machine-readable source facts (not a runtime test).
- No successful run is claimed by the arithmetic rows alone.
Unmeasured states are stated explicitly; this page does not invent run scores or compatibility guarantees.
Which date applies to which fact
- Committed page-copy sources:
- Upstream model metadata: Dates on artifact records when shown; not implied by page-copy revision
- Run receipts: Only on /evidence pages when recorded; otherwise unmeasured
Page-copy revision (Updated line above) identifies committed text sources, not upstream model edits or test outcomes.
We read what this browser can tell us, then match one hosted file from the catalog.
Is this detected device correct for your computer?
Confirm your device, then choose:
- Chat
- Coding
- Images or other
Your answers stay in this tab. File size is from the catalog, not a promise it will run smoothly.