Alibaba
Qwen3.5 2B
Qwen instruction model for multilingual chat and tool use
Model facts
- Context window
- 262K tokens
- Maximum output
- 262K tokens
- Cheapest paid input
- $0.02 per 1M tokens
- Cheapest paid output
- $0.1 per 1M tokens
- Open weights
- yes
- Providers
- 3
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image.
Local hardware estimate
At 4K context: Q4_K_M 2.4 GiB, Q8_0 3.4 GiB, F16 5.4 GiB working memory.
- Parameters
- 2.3 billion
- Architecture
- qwen3_5
- Model license
- apache-2.0
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| Reasoning | 7.4 | 2.9 | not measured | not measured |
| Non-reasoning | 5.3 | 2.4 | not measured | not measured |
Observed price history
- 2026-08-24: $0.018 input / $0.09 output per 1M tokens
- 2026-08-28: $0.02 input / $0.1 output per 1M tokens
API providers
- QVAC — model id qwen3.5-2b; free input / free output per 1M tokens; provider documentation
- Requesty — model id qwen3.5-2b; $0.02 input / $0.1 output per 1M tokens; provider documentation
- NanoGPT — model id qwen3.5-2b; $0.08 input / $0.16 output per 1M tokens; provider documentation