Run Qwen3.5 0.8B on Android and iPhone
Qwen3.5 0.8B running on real Android phones: measured tokens per second, peak memory, the RAM it needs, and how to install it. MNN build, 0.6 GB on disk.
TokForge is free. Android is on Google Play open testing; iPhone and iPad are in open TestFlight beta. No account, and it works with the network off once a model is downloaded.
Reading on a computer? See real measured speeds on the phone-speed leaderboard.
What Qwen3.5 0.8B is good at
Short questions, quick rewrites, summarising a paragraph, and anything where you want the answer before you have finished reading the question. It is the smallest chat model in the app and the one to reach for on older or budget hardware. It is not the model to hand a long document or a multi-step reasoning problem.
Builds TokForge ships
| Build | Format | Download size | RAM floor | Source repo |
|---|---|---|---|---|
| Qwen3.5 0.8B | MNN | 0.6 GB | 4 GB | taobao-mnn/Qwen3.5-0.8B-MNN |
Download sizes and RAM floors are the values the shipping app uses, taken from the catalogue in build v3.6.0-beta142. The RAM floor is a gate, not a suggestion: below it the model does not appear in the app at all.
What real phones record
These are submissions from the benchmark built into TokForge, not estimates and not numbers from a press release. Each row carries the handset, the chip, the app build and the date it was submitted. The table refreshes from the live board when you load this page; the version printed in the HTML is a snapshot taken on 2026-07-27.
| Device | SoC | Engine | Decode tok/s | Prefill tok/s | Peak RAM | App build | Submitted |
|---|---|---|---|---|---|---|---|
| SM-S948U | SM8850 | MNN | 74.92 | 117.6 | 0.7 GB | v3.6.0-beta130 | 2026-07-15 |
| SM-G988U | SM8250 | MNN | 38.30 | - | 0.7 GB | v3.6.0-beta130 | 2026-07-14 |
| V2270A | SM7325 | MNN | 24.40 | 74.7 | 0.7 GB | v3.6.0-beta120 | 2026-07-08 |
Decode tokens per second is the speed you feel while an answer is being written. Prefill is how fast it reads what you sent. A dash means the submission did not carry that field. Peak RAM is what the process actually touched, and it is left blank where the reported figure is too small to be a real measurement of a model this size.
Open the full phone-speed leaderboard
Which phones can run it
It is the model TokForge puts in front of a 4 GB phone, which is the smallest tier the app serves. TokForge snaps your device to a RAM tier and hides anything above it, so the honest answer to "will it run on mine" is: if your phone reports 4 GB or more, the app will offer it to you. Whether it runs well is a separate question, and the table above is the place to look for a handset close to yours.
If you want the arithmetic rather than the rule of thumb, the phone RAM calculator works through weights, cache and operating system overhead for any model in the catalogue, and is explicit about how wide its error bars are.
How to run it
- Install TokForge. Android is on Google Play open testing, iPhone and iPad are on TestFlight.
- Open the model manager. Qwen3.5 0.8B appears if your device clears the 4 GB floor.
- Download it once over Wi-Fi, then turn the network off if you like. It keeps working.
You are not limited to the catalogue. TokForge browses Hugging Face inside the app and imports GGUF and MNN files you already have, so any other build of this model is a search away.
Common questions
How much RAM does Qwen3.5 0.8B need on a phone?
TokForge will not offer Qwen3.5 0.8B to a device with less than 4 GB of RAM. That floor is the app’s own gate, not an estimate: below it the model is hidden rather than allowed to fail halfway through loading. Total RAM is not the whole story, because the operating system keeps a large share of it and a backgrounded app gets less again, so treat 4 GB as the minimum rather than the comfortable number. Handsets that have already recorded a run of it on the public board include SM-S948U, SM-G988U, V2270A.
How fast is Qwen3.5 0.8B on a phone?
That depends entirely on the handset, so we do not publish a single number for it. Every speed figure on this page is a submission from a real device through the benchmark built into the app, carrying the device, the SoC, the app build and the date. The live table above is the answer, and the full board is at /leaderboard/.
Can I run Qwen3.5 0.8B on an iPhone?
TokForge for iPhone and iPad is in open TestFlight beta, and it is not on the App Store yet. The model catalogue and the RAM floors are the same on both platforms. iOS is stricter about memory than Android is, so a model that is marginal on an Android phone with the same amount of RAM will be more marginal on iOS.
Does Qwen3.5 0.8B work offline?
Yes. The download needs a network. After that the model runs on the handset with the radios off, and nothing about the conversation leaves the device.