Run WizardMath 7B V1.1 in your browser
WizardMath 7B V1.1 is a 7B WizardLM model. In the browser it downloads 3.8 GB and needs about 4.5 GB of GPU memory.
Use WizardMath 7B V1.1 in the browser All models Downloads once · then works offline
- Family
- WizardMath
- Published by
- WizardLM
- Parameters
- 7B
- Quantisation
- q4f16_1 · 4-bit
- Download
- 3.8 GB · 107 files
- GPU memory
- 4.5 GB
- Context window
- 4k tokens
- Reasoning
- —
- Licence
- See the model card
- Base model
- WizardLMTeam/WizardMath-7B-V1.1
- Good at
- Chat · Maths
| # | Build | Download | |
|---|---|---|---|
| 01 | q4f16_1 | 3.8 GB | Recommended |
How big is the WizardMath 7B V1.1 download?
3.8 GB for the q4f16_1 build, in 107 files. It downloads once and stays in your browser cache, so every later visit starts straight away and works offline.
What does my device need to run WizardMath 7B V1.1?
A browser with WebGPU (a recent Chrome, Edge, Firefox or Safari) and about 4.5 GB of GPU memory. Before anything downloads, the tool checks your GPU, memory and free space and tells you whether WizardMath 7B V1.1 fits.
Is anything I type sent to a server?
No. WizardMath 7B V1.1 runs on your own GPU inside the browser tab. The only network traffic is the one-time download of the model files from Hugging Face; your prompts and the answers never leave the device, and the chats are stored in this browser.
How long a conversation can WizardMath 7B V1.1 hold?
Its context window is 4k tokens. Longer conversations still work: once the conversation no longer fits, the oldest turns are dropped and you see a notice.
Figures read from the WebLLM 0.2.84 catalog and the model card on 2026-09-03.
