Qwen3.5 0.8B

Find hardware that runs Qwen3.5 0.8B on your budget

Reference: Model card on Hugging Face

Parameters
0.87 B
Active per token
0.87 B
Architecture
Dense
Modality
vision
Max context
262144
Released
2026-03-01
License
apache-2.0

Measurements

Decode is token generation — the speed you feel while an answer streams. Prefill is prompt processing — the wait before it starts. Why bandwidth predicts decode speed.

What verified, single-source and estimated mean, and the same rows with every filter and sort in the benchmarks explorer.

Speed over time

Cheapest hardware by target speed

The lowest-priced entry that reaches each threshold, using the strongest evidence available. Estimated rows are marked.