“First query answered with ease by 4bit Qwen2.5 32B running on my M4 max in just a few seconds: https://x.com/awnihannun/status/1895487722963484697
“QwQ-32B evals on par with Deep Seek R1 680B but runs fast on a laptop. Delivery accepted. Here it is running nicely on a M4 Max with MLX. A snippet of its 8k token long thought process: https://x.com/awnihannun/status/1897394318434034163
“Second query also answered with ease, same model, same device: https://x.com/awnihannun/status/1895494505543110847
“🔥 You can already try out QwQ-32B on @huggingface with inference! Test its reasoning & problem-solving capabilities yourself! https://x.com/fdaudens/status/1897394462650999029
“FRESH FROM THE OVEN: Just deployed QwQ 32B on Hugging Chat 💯 Give it a shot – the vibes are strong with this one! https://x.com/reach_vb/status/1897686816037167394
“Vibe coding app with Qwen QwQ-32B in a few lines of code https://x.com/_akhaliq/status/1897774596515938394
“🔥 Just released: QwQ-32B achieves DeepSeek-R1’s performance with just 32B parameters (vs 671B)! This breakthrough in Reinforcement Learning scaling proves smaller models can match giants in reasoning & problem-solving. https://x.com/fdaudens/status/1897365520728605153
“Welcome, Qwen QwQ-32B! 👋Excited to have the latest @Alibaba_Qwen in the Arena ready to chat with everyone. https://x.com/lmarena_ai/status/1897763753417900533
“Qwen 32B QwQ – no. 1 trending on Hugging Face – SoTA after SoTA, the competition is heating up! 🔥 GG @Alibaba_Qwen https://x.com/reach_vb/status/1897974348503208081
“developers can get started with pip install –upgrade “ai-gradio[huggingface]” export HF_TOKEN import gradio as gr import ai_gradio gr.load( name=’huggingface:Qwen/QwQ-32B’, src=ai_gradio.registry, coder=True, provider=”hyperbolic” or fireworks-ai ).launch() github:” / X https://x.com/_akhaliq/status/1897775110033227860
QwQ-32B: Embracing the Power of Reinforcement Learning | Qwen https://qwenlm.github.io/blog/qwq-32b/
“New Open Reasoning Model that can run locally! @Alibaba_Qwen QwQ 32B close to @deepseek_ai R1 and @OpenAI o1 mini while only needing 32B parameter, while being extremely cheap, with $0.20/M tokens (input & output). TL;DR: 🧠 QwQ-32B matches DeepSeek-R1 and OpenAI o1-mini with https://x.com/_philschmid/status/1897556185126932750
“Alibaba just dropped START Self-taught Reasoner with Tools we have fine-tuned the QwQ-32B model to achieve START. On PhD-level science QA (GPQA), competition-level math benchmarks (AMC23, AIME24, AIME25), and the competition-level code benchmark (LiveCodeBench), START achieves https://x.com/_akhaliq/status/1897854193152438553
“Our new Aya 32B outperforms llama 90B and qwen 72b 👀 https://x.com/nickfrosst/status/1896935581386682827
“Having endless repetitions with QwQ-32B? I made a guide to help debug stuff! When using repetition penalties to counteract looping, it rather causes looping! Try adding this to llama.cpp: –samplers “top_k;top_p;min_p;temperature;dry;typ_p;xtc” I also uploaded dynamic 4bit https://x.com/danielhanchen/status/1898035752124166368
