When was Qwen3.5-2B released?

Qwen3.5-2B was released on March 2, 2026 by Qwen. This is the official Qwen3.5-2B release date tracked on LLM Stats.

Is Qwen3.5-2B available via API?

Yes, Qwen3.5-2B is available via API. See the official documentation for authentication and endpoint details.

How big is Qwen3.5-2B?

Qwen3.5-2B has 2 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Qwen3.5-2B?

Qwen3.5-2B was created by Qwen.

What is the license for Qwen3.5-2B?

Qwen3.5-2B is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Is Qwen3.5-2B multimodal?

Yes, Qwen3.5-2B is multimodal and can accept both text and images as input.

What models should I compare Qwen3.5-2B against?

Common Qwen3.5-2B comparisons include Qwen3.5-2B vs Llama 3.1 70B Instruct, Qwen3.5-2B vs Gemini 1.5 Flash, Qwen3.5-2B vs Phi 4 Mini Reasoning. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.

Qwen3.5-2B API Pricing, Context Window & Benchmarks

Name: Qwen3.5-2B
Author: Qwen

Qwen3.5-2B: API Pricing, Context Window & Benchmarks

Qwen3.5-2B is a language model from Qwen, released in March 2026, with multimodal input.

Qwen3.5-2B is a 2 billion parameter vision-language model using Gated DeltaNet hybrid architecture with a 3:1 ratio of linear attention to full softmax attention. It supports 262K native context length and features both thinking and

Qwen3.5-2B benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Qwen3.5-2B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Qwen3.5-2B holds up as conversations get longer.

Quality Tracker

Qwen3.5-2B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Tue Sep 08 2026

Notice missing or incorrect data?

Qwen3.5-2B model size

Qwen3.5-2B has 2 billion parameters. See how it compares to other models in the same parameter range.

Parameters

Small (<3B)

1B7B70B405B

Qwen3.5-2B API

Available from the model provider

Qwen3.5-2B has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

Qwen3.5-2B latency

Qwen3.5-2B time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Qwen3.5-2B examples

Recent arena outputs from Qwen3.5-2B, picked from the highest-ranked matchups.

Qwen3.5-2B license

Qwen3.5-2B is released under the Apache 2.0 license, which permits commercial use, has 2.0B parameters.

License: Apache 2.0; Commercial use allowed
Parameters: 2.0B

Apache License 2.0 - allows commercial use

Qwen3.5-2B resources

Official sources for Qwen3.5-2B: api documentation, official playground, source repository, model weights.

Qwen3.5-2B vs other models

The most-compared alternatives to Qwen3.5-2B are Llama 3.1 70B Instruct, Gemini 1.5 Flash, Phi 4 Mini Reasoning. Open any pair side-by-side for benchmarks, pricing, context, and latency.