AMD reported that UltraQuant, its 4-bit KV-cache method for the Qwen3.8-2.4T MXFP4 model on AMD Instinct MI355X GPUs, serves 29% more tokens per second at 24% lower per-token latency than the fastest …
On August 12th, Alibaba Cloud's Qwen team released Qwen3.8-2.4T-A95B, an open-weight mixture-of-experts model with 2.4 trillion total parameters and 95 billion active during inference, making it the f…
Alibaba published the first Max-class Qwen model as downloadable weights on August 12, but under a custom Qwen3.8-Max License with revenue thresholds, not Apache 2.0. The text-only checkpoint, Qwen3.8…
Alibaba released the open-weight Qwen3.8-27B multimodal model on 2026-08-05 under Apache-2.0, featuring a 27B dense architecture with a vision encoder, 262,144-token native context, and hybrid thinkin…
Unsloth released dynamic GGUF quantizations for Qwen3.8, enabling the 27B model to run locally on 17-19GB VRAM setups and the 2.4T parameter model to run in 397GB via 1-bit quantization. The Qwen3.8 f…
Alibaba's Qwen team released Qwen3.8-27B, a 28-billion-parameter image-text-to-text model, on Hugging Face, with an FP8 quantized version also available. The model is part of the Qwen3.8 collection, w…
Alibaba's Qwen project scheduled the release of Qwen3.8-27B, a dense 27-billion-parameter vision-language model, for August 14, 2026, according to a countdown post from the official Qwen account. The …
Alibaba's Qwen team released the open weights for Qwen3.8-2.4T-A95B, a 2.4T-parameter MoE flagship, on August 13, 2026, and Fixstars deployed it on a single 8x NVIDIA B300 node, achieving twice the th…
Alibaba Group Holding Ltd. released the Qwen3.8-2.4T-A95B open-weights model under a restrictive custom Qwen3.8-Max License, requiring businesses with over $50 million in annual revenue to negotiate a…
Alibaba's Qwen team released Qwen3.8-2.4T-A95B, an open-weight mixture-of-experts model with 2.4 trillion total parameters and 95 billion activated per token, which scores 93.0 on PaperBench and 86.6 …
Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), a 2.4T-parameter mixture-of-experts model with 95B activated parameters per token, designed for long-context reasoning and agenti…
Alibaba released the open-source Qwen3.8-2.4T-A95B model weights on August 12, a 2.4-trillion-parameter sparse mixture-of-experts model with about 95 billion active parameters per token, making it the…
Alibaba's Qwen team released Qwen3.8-2.4T-A95B, an open-weight mixture-of-experts language model with 2.4 trillion total parameters and 95 billion active per token, supporting 262,144 tokens of native…
Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter mixture-of-experts model with 95 billion active parameters per token, requires roughly 4.8 terabytes of memory at FP16/BF16 for weights alone, making local …