Qwen3.5 0.8B
873M parameters · 256k context · Apache License 2.0 · released 2026-02-28
chatvisionagenticreasoning
What to run it on in the US
Fully in memory at 8k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
Small 0.8B model the card says is meant for prototyping, fine-tuning and research; it defaults to non-thinking mode and is more prone to thinking loops in thinking mode. Needs the main branch of vLLM/SGLang or the latest transformers.
Questions
- What licence is Qwen3.5 0.8B released under?
- Apache License 2.0, which allows commercial use.