Qwen3.5 2B
Qwen3.5 2BRankingin non-thinking mode?
Alternatives?
CheaperGPT OSS 20BlowOpen+61%-10%$0.018 / $0.09Context: 262K → 131K+2BetterGPT-6 Lunalow×3.5+400%$0.005Function calling only with none · Chat Completions+3IOpenK2 Horizon 7Bthinking×3.3+1,212%$0.30 / $1.20Memory (4-bit): 1.1 GB → 4.5 GB+1CheaperQwen3.5 0.8BthinkingOpensame-50%$0.01 / $0.05
BetterGranite 4.2 3BthinkingOpen+46%+31%$0.006Context: 262K → 128K+2GPT OSS 20BlowOpen+61%-10%$0.018 / $0.09Context: 262K → 131K+2Qwen3.5 0.8BthinkingOpensame-50%$0.01 / $0.05GPT-6 Lunalow×3.5+400%$0.005Function calling only with none · Chat Completions+3Granite 4.2 3BthinkingOpen+46%+31%$0.006Context: 262K → 128K+2
Gemma 4 E4BthinkingOpen+44%same$0.008Context: 262K → 128K+1GPT-5.6 Lunalow×3.4+1,025%$0.01GPT OSS 20BhighOpen+45%-10%$0.011Context: 262K → 131K+2Gemma 4 12BthinkingOpen×2.3+275%$0.10 / $0.30Context: 262K → 256K+1Qwen 3.5 9Bnon-thinkingOpen×2.1+131%$0.08 / $0.13Memory (4-bit): 1.1 GB → 4.8 GBQwen3.5 4BthinkingOpen×2.1+50%$0.03 / $0.15Memory (4-bit): 1.1 GB → 2.3 GBQwen3.8 Max (0902)thinking×7.3—$5.41Qwen3.8 2.4T A95BthinkingOpen×6.5—$2.16Memory (4-bit): 1.1 GB → 1,468 GB+6Qwen3.8 FlashthinkingOpen×6.4—$0.37Memory (4-bit): 1.1 GB → 108 GB+6Qwen3.7 Maxthinking×4.8—$1.15No image inputQwen3.6 Max Previewthinking×4.6—$1.30 / $7.80No image input+1Qwen3.8 27BmediumOpen×4.5—$1.13Memory (4-bit): 1.1 GB → 17 GB+5Qwen3.6 Plusthinking×4.4—$0.50 / $3Qwen3.7 Plusthinking×4.1—$0.22All Alibaba (Qwen) models →Run it yourself
estimateBenchmarks
all categoriesFAQ
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?›
#275 of 334 in Chat & Knowledge, #171 of 239 in Coding, #122 of 175 in Agents & Tool Use, #213 of 245 in Writing & Language, #117 of 124 in Vision & Documents.
Is Qwen3.5 2B better than Qwen3 1.7B?›
On AA Intelligence Index 4.3.2, Qwen3.5 2B scores 6.9 vs 5.2 — higher.
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 OSS 20B (cheaper), GPT-6 Luna (better), K2 Horizon 7B (open weights).