Qwen3.5 2B

Mar 2026
Qwen3.5 2B
Compare in
on
—per task?
$0.02 / $0.10per 1M in / out?
—output speed?
262Kcontext

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use

FAQ

How much does Qwen3.5 2B cost?›

$0.02 per 1M input tokens and $0.10 per 1M output tokens (cheapest host: DeepInfra).

Is Qwen3.5 2B free to use?›

There is no free API; the cheapest paid price is $0.02 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Qwen3.5 2B, and what is it best at?›

#330 of 334 in Chat & Knowledge, #171 of 239 in Coding, #122 of 175 in Agents & Tool Use, #206 of 245 in Writing & Language, #117 of 124 in Vision & Documents.

Is Qwen3.5 2B better than Gemini 3.6 Flash?›

On MathArena · BrokenArXiv · June 2026, Qwen3.5 2B scores 2.8 vs 12 — about the same.

How can I use Qwen3.5 2B?›

Through the API of DeepInfra, Featherless.

What is the context window of Qwen3.5 2B?›

262K tokens.

When was Qwen3.5 2B released? Is there a newer version?›

Released 2026-03-02. It is the current version in its line.

Is Qwen3.5 2B open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Qwen3.5 2B locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Qwen3.5 2B read images?›

It accepts text and images as input.

What is Qwen3.5 2B?›

Qwen3.5 2B is an open-weights language model from Alibaba (Qwen), released Mar 2026, the successor to Qwen3 1.7B.

What are the best alternatives to Qwen3.5 2B?›

GPT-6.1 Sol (better).