Alibaba's Qwen announced releasing the quantised models of Qwen3 AI today which were deployed via LM Studio, Ollama, SGLang and vLLM platforms. The interested users can choose from multiple formats, such as GGUF (GPT-Generated Unified Format), AWQ (Activation-aware Weight Quantisation), and GPTQ (Gradient Post-Training Quantisation). The Qwen3 quantised models include Qwen3-235B-A22B, Qwen3-30B-A3B, Qwen3-32B, Qwen3-14B, Qwen3-8B, Qwen3-4B, Qwen3-alks-about-creating-with-his-son-abhishek-bachchan-6940221.html" class="drop-thumb-link" title="‘Biggest Learning and the Biggest Blessing’: Megastar Amitabh Bachchan Talks About Creating With His Son Abhishek Bachchan">‘Biggest Learning and the Biggest Blessing’: Megastar Amitabh Bachchan Talks About Creating With His Son Abhishek Bachchan
Qwen3 Quantised Models Released: Alibaba’s Qwen Launches Multiple AI Models in Various Formats via LM Studio, Ollama, SGLang and vLLM
Alibaba’s Qwen has launched quantised models of Qwen3 AI, now available through platforms like LM Studio, Ollama, SGLang, and vLLM. Users can choose from multiple formats, including GGUF, AWQ, and GPTQ. The models range from Qwen3-235B-A22B to Qwen3-0.6B, offering various sizes for different needs.
