Run DeepSeek R1 Distill 7B in your browser
Always thinks before answering; the reasoning streams into a collapsible block.
Use DeepSeek R1 Distill 7B in the browser All models Downloads once · then works offline
- Family
- DeepSeek R1
- Published by
- DeepSeek
- Parameters
- 7B
- Quantisation
- q4f16_1 · 4-bit
- Download
- 4.0 GB · 88 files
- GPU memory
- 5.0 GB
- Context window
- 4k tokens
- Reasoning
- Always
- Licence
- MIT
- Base model
- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
- Good at
- Chat · Reasoning
How big is the DeepSeek R1 Distill 7B download?
4.0 GB for the q4f16_1 build, in 88 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 DeepSeek R1 Distill 7B?
A browser with WebGPU — recent Chrome, Edge, Firefox or Safari — and about 5.0 GB of GPU memory. The tool checks your GPU, memory and free space and tells you whether DeepSeek R1 Distill 7B fits before anything downloads.
Is anything I type sent to a server?
No. DeepSeek R1 Distill 7B 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.
Which build of DeepSeek R1 Distill 7B should I choose?
Start with q4f16_1 — it is the smallest download and the fastest to run. The f32 builds are larger and use more memory, but they run on GPUs without 16-bit shader support. Builds marked 1k hold a shorter conversation in exchange for less memory.
How long a conversation can DeepSeek R1 Distill 7B hold?
Its context window is 4k tokens. Longer conversations keep working — the oldest turns are dropped with a notice when the conversation no longer fits.
Does DeepSeek R1 Distill 7B show its reasoning?
DeepSeek R1 Distill 7B always thinks before it answers. The reasoning streams into a collapsible block above the answer and is never sent back as part of the conversation.
What licence is DeepSeek R1 Distill 7B released under?
The weights are MIT, taken from the model card of deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. Check the licence yourself before using it commercially.
Figures read from the WebLLM 0.2.84 catalog and the model card on 2026-09-03.
