#qwen3_5 — Public Fediverse posts

@john #ollama is garbage, #qwen3_5 has many fixes in #llamacpp recently, it is not fully ready yet

Alibaba just released the Qwen‑3.5‑Medium model as open‑source, delivering Sonnet 4.5‑level performance on a single GPU. It uses a Mixture‑of‑Experts architecture and a new “Thinking Mode” to boost AI inference efficiency while staying lightweight. Dive into the details and see how this could reshape open‑source LLM development. #Qwen3_5 #OpenSourceLLM #MixtureOfExperts #ModelEfficiency

🔗 https://aidailypost.com/news/alibaba-open-sources-qwen35-medium-models-sonnet-45-performance

Alibaba's new Qwen 3.5 397B-A17 outperforms even larger rivals by using multi-token prediction and a sparse mixture-of-experts architecture. It cuts inference cost while keeping top-tier performance, hinting at a new era for multimodal AI. Curious how 397 billion parameters can be cheaper? Read the full story. #Qwen3_5 #AlibabaAI #MixtureOfExperts #MultiTokenPrediction

🔗 https://aidailypost.com/news/alibabas-qwen-35-397b-a17-beats-larger-model-via-multitoken

Alibaba's new Qwen 3.5 397B-A17 outperforms even larger rivals by using multi-token prediction and a sparse mixture-of-experts architecture. It cuts inference cost while keeping top-tier performance, hinting at a new era for multimodal AI. Curious how 397 billion parameters can be cheaper? Read the full story. #Qwen3_5 #AlibabaAI #MixtureOfExperts #MultiTokenPrediction

🔗 https://aidailypost.com/news/alibabas-qwen-35-397b-a17-beats-larger-model-via-multitoken

Alibaba's new Qwen 3.5 397B-A17 outperforms even larger rivals by using multi-token prediction and a sparse mixture-of-experts architecture. It cuts inference cost while keeping top-tier performance, hinting at a new era for multimodal AI. Curious how 397 billion parameters can be cheaper? Read the full story. #Qwen3_5 #AlibabaAI #MixtureOfExperts #MultiTokenPrediction

🔗 https://aidailypost.com/news/alibabas-qwen-35-397b-a17-beats-larger-model-via-multitoken