AI Model2026-05-17
Qwen (Alibaba)
Also known as: Qwen (Alibaba) / Alibaba Qwen / Qwen3
Alibaba Cloud's open-weights LLM series. The Qwen 3.5 and 3.6 generation scored above Claude Opus on agentic coding benchmarks and delivers strong Japanese-language performance.
Overview
Qwen 3.6-27B Dense achieves 40 tok/s on an RTX 3090 and leads agentic coding benchmarks. It is also attracting attention for reducing in-house AI infrastructure costs. See Qwen 3.6-27B release.
Model variants
Offered in diverse sizes — 9B SLM, 27B Dense, 35B-A3B MoE, and 72B — all runnable on commodity hardware including Mac mini via Ollama.
Related Columns
AI
Qwen 3.6-27B Released — Dense 27B Leads Agentic Coding, 40 tok/s on RTX 3090 [April 2026]
Qwen 3.6-27B Dense from Alibaba's Qwen Team, released April 22, 2026: 77.2 on SWE-bench Verified, 59.3 on Terminal-Bench 2.0 (matching Claude 4.5 Opus), 262K-to-1M context, Apache 2.0 license, and 40 tok/s on an RTX 3090 with Q4_K_M — summarized from official sources.
AI
Qwen3.5-9B Complete Guide: Run on Ollama with Just 5GB — Features, Benchmarks & Use Cases
Comprehensive guide to Qwen3.5-9B: Ollama setup instructions, hybrid Gated DeltaNet + Sparse MoE architecture, 262K context window, GPQA 81.7 and IFBench 76.5 (beating GPT-5.2's 75.4), comparison with GPT-4o-mini and Claude Haiku, and practical business use cases. Runs on just 5GB RAM.
AI
Gemma 4 vs Llama 4 vs Qwen 3.5 Comparison — 2026 Local LLM Selection Guide
Comprehensive comparison of Gemma 4, Llama 4, and Qwen 3.5 local LLMs. Detailed analysis of benchmark performance, licensing, Japanese support, hardware requirements, and use case selection criteria.
AI
Qwen-Image-2.1 Requirements, VRAM & How to Use (7B Unified Generation + Editing, Sep 2026)
Qwen-Image-2.1, Alibaba's open model (Sep 20, 2026), unifies 7B gen and editing with transparent PNG, 10-image edits. VRAM unofficial; non-commercial license.
AI
Qwen3.8-Omni-Flash: 1M Context, Pricing & Closed Weights
Qwen3.8-Omni-Flash: Alibaba's omni-modal model, 1M-token context, $0.15/million input. Weights closed, no local run; text-only output, unlike its predecessor.
AI
Perplexity Hybrid Compute Explained: How PPLX Qwen 3.8 27B Splits AI Tasks Between Cloud and Mac
As of Sep 2026, Perplexity's Hybrid Compute feature for the Mac Computer agent starts tasks in the cloud and hands off only the steps involving sensitive data to a local model (PPLX Qwen 3.8 27B) on Apple Silicon. This article explains, based on primary sources, how the local/cloud boundary is decided, the hardware requirements, and how it differs from Apple's Private Cloud Compute and fully local setups.
Feel free to contact us
Contact Us