Qwen3.5 0.8B
Qwen3.5 0.8BRankingin non-thinking mode?
Alternatives?
BetterGPT-6 Lunalow×4+900%$0.005Function calling only with none · Chat Completions+3IOpenK2 Horizon 7Bthinking×3.8+2,525%$0.30 / $1.20Memory (4-bit): 0.4 GB → 4.5 GB+1
BetterGranite 4.2 3BthinkingOpen+68%+163%$0.006Context: 262K → 128K+2
BetterGemma 4 E4BthinkingOpen+65%+100%$0.008Context: 262K → 128K+1BetterGPT-5.6 Lunalow×3.9+2,150%$0.01GPT-6 Lunalow×4+900%$0.005Function calling only with none · Chat Completions+3Granite 4.2 3BthinkingOpen+68%+163%$0.006Context: 262K → 128K+2Gemma 4 E4BthinkingOpen+65%+100%$0.008Context: 262K → 128K+1GPT-5.6 Lunalow×3.9+2,150%$0.01GPT OSS 20BhighOpen+66%+80%$0.011Context: 262K → 131K+2Gemma 4 12BthinkingOpen×2.6+650%$0.10 / $0.30Context: 262K → 256K+1Qwen 3.5 9Bnon-thinkingOpen×2.5+363%$0.08 / $0.13Memory (4-bit): 0.4 GB → 4.8 GBQwen3.5 4BthinkingOpen×2.4+200%$0.03 / $0.15Memory (4-bit): 0.4 GB → 2.3 GBQwen3.8 Max (0902)thinking×8.4—$5.41Qwen3.8 2.4T A95BthinkingOpen×7.4—$2.16Memory (4-bit): 0.4 GB → 1,468 GB+6Qwen3.8 FlashthinkingOpen×7.4—$0.37Memory (4-bit): 0.4 GB → 108 GB+6Qwen3.7 Maxthinking×5.5—$1.15No image inputQwen3.6 Max Previewthinking×5.3—$1.30 / $7.80No image input+1Qwen3.8 27BmediumOpen×5.1—$1.13Memory (4-bit): 0.4 GB → 17 GB+5Qwen3.6 Plusthinking×5—$0.50 / $3Qwen3.7 Plusthinking×4.7—$0.22All Alibaba (Qwen) models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Qwen3.5 0.8B cost?›
$0.01 per 1M input tokens and $0.05 per 1M output tokens (cheapest host: DeepInfra).
Is Qwen3.5 0.8B free to use?›
There is no free API; the cheapest paid price is $0.01 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Qwen3.5 0.8B, and what is it best at?›
#267 of 334 in Chat & Knowledge, #210 of 239 in Coding, #122 of 175 in Agents & Tool Use, #238 of 245 in Writing & Language, #124 of 124 in Vision & Documents.
Is Qwen3.5 0.8B better than Qwen3 0.6B?›
On AA Intelligence Index 4.3.2, Qwen3.5 0.8B scores 6.1 vs 4.8 — higher.
How can I use Qwen3.5 0.8B?›
Through the API of DeepInfra.
What is the context window of Qwen3.5 0.8B?›
262K tokens.
When was Qwen3.5 0.8B released? Is there a newer version?›
Released 2026-03-02. It is the current version in its line.
Is Qwen3.5 0.8B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Qwen3.5 0.8B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Qwen3.5 0.8B read images?›
It accepts text and images as input.
What is Qwen3.5 0.8B?›
Qwen3.5 0.8B is an open-weights language model from Alibaba (Qwen), released Mar 2026, the successor to Qwen3 0.6B.
What are the best alternatives to Qwen3.5 0.8B?›
GPT-6 Luna (better), K2 Horizon 7B (open weights).