AI is changing the world. Don't stay behind. Clear summaries, community insight, delivered without the noise. Subscribe to never miss a beat.

Privacy

Contact

Back to all news

llms alibaba open-source developer-tools

Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

Alibaba's new open source Qwen3.5 Medium model offers near Sonnet 4.5 performance on local computers

venturebeat.com

February 28, 2026

5 min read

🔥🔥🔥🔥🔥

66/100

Summary

Alibaba released the Qwen3.5 Medium Model series, which includes four large language models (LLMs) that support agentic tool calling. Three of these models, Qwen3.5-35B-A3B, Qwen3.5-122B-A10B, and Qwen3.5-27B, are available for commercial use under the Apache 2.0 license and can be downloaded from Hugging Face and ModelScope.

Key Takeaways

Alibaba released the Qwen3.5 Medium Model series, which includes four large language models that support agentic tool calling and are available under the Apache 2.0 open source license.
The Qwen3.5-35B-A3B model can exceed a 1 million token context length on consumer-grade GPUs with 32GB of VRAM, offering high performance comparable to proprietary models from major U.S. startups.
Qwen 3.5 features a "Thinking Mode" that generates an internal reasoning chain before providing answers, enhancing its logical processing capabilities.
The models maintain high accuracy even when quantized to 4-bit weights, significantly reducing memory footprint for local deployment.

Read original article

Community Sentiment

Mixed

Positives

The new 35B model demonstrates great performance for tool use, indicating its practical applications in various domains.
Opus 4.6 and Gemini Pro deliver satisfactory results quickly, showcasing the potential for local AI models to provide valuable insights.

Concerns

Running the Qwen 3.5 model on local hardware resulted in a lengthy 45-minute processing time with a generic answer, raising concerns about efficiency.
There are slight incompatibilities with Claude Code in the new 35B model, which could hinder seamless integration for developers.