Tracked topic
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
…commands, or perform live video analysis — it is a large language model at its core. Challenge Complete Your Score / 8 Thanks for playing! Tool calling is another important reason Qwen 2.5…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in parallel, and are then verified by the target model…
…Related I tested Qwen3 Coder Next against four other local AI coding models, and the gap was embarrassing Qwen3 Coder Next is one of the best local models out there, and it…
…6 enhances document parsing performance through targeted data optimization and progressive post-training techniques, achieving state-of-the-art results on OmniDocBench v1.6. Generated by Qwen/Qwen2.5-Coder-32B-Instruct…
Looking for V100 users to share your config and it's performance. GPU: Tesla V100 PCIE 32Gb Qwen3.6 27B Q4_K_M + Q8_0 MTP 128K context length Pi coding agent llama.cpp model preset: [*] spec-default = 1 ctx-size = 131072…
Qwen3.8-Max (2.4T) is another massive contribution to the open weight community. On benchmarks, it performs closely to Kimi K3 and DeepSeek V4 flash across all categories and is better at coding and software tasks. Qwen3…
QwQ was genuine next-gen performance usable on local hardware, but the massive required context (it's reasoning style was akin to "if I say every possible word, I'll notice the right one!") kinda made it unusable for age…
…Qwen3 14B and 8B were the top local performers. Mistral 7B v0.3 was one of the first open-weight models with native function-calling tokens, and it still works. It's…
…Jetson Thor delivers optimized performance across Qwen models like the Qwen 3.5-35B-A3B model, which reasons at 35 tokens per second, making real-time interactivity possible. Any developer can fine…
…On benchmarks, Qwen's own results have the 27B dense model edging ahead of the previous Qwen3.5-397B-A17B MoE on SWE-bench Verified, at 77.2% versus 76.2%. That…
…Following Gemma 3’s massive failure, I moved back to the Qwen architecture with Qwen3 Thinking (4B). Well, specifically the Qwen3-4B-Thinking-2507-Q4_K_M model, as I’ve heard…
…Thanks! If you feel interested, can be reached out by chenyang.zhao@sglang.ai Would also be nice to include the performance of Qwen2.5-Math-Instruct and Qwen2.5-7B-Instruct…
…startup PrismML has released Bonsai 27B, an extremely compressed AI model based on Alibaba’s Qwen3.6. The smallest version takes up just 3.9 GB, making it the first to fit…
