Qwen3.5-0.8B
> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. > > In light of its parameter scale, the intended use cases are prototyping, task-specific fine-tuning, and other research or development purposes.
Params
870 M
Context
—
Downloads 30d
3.5 M
Likes
827
Download history
daily snapshots · 106 days
▲ 989 K in the last 30 days (38.6%)
3.8 M2.6 M
Oct 12Oct 22Nov 1Nov 10
3.8 M2.3 M
Aug 13Sep 12Oct 12Nov 10
3.8 M2.3 M
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 1.7 GB | 2.6 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Qwen3_5ForConditionalGeneration
- Parameters
- 870 M
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-02-28
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any image-text-to-text model