Alibaba Releases FP8 Quantized Qwen3.8-Flash-Next Model
Qwen · hf · 2026-08-27
Alibaba's Qwen team released the Qwen3.8-Flash-Next-FP8 model on Hugging Face. It is an FP8-quantized version of the Qwen3.8-Flash-Next base model, featuring an image-text-to-text pipeline for multimodal conversational tasks and endpoint compatibility.
More from Models
- AutoClaw Integrates GLM-5.3-Flash with Limited-Time Rewards — Zai_org · 2026-08-27
- TIME Deep Dive: Inside OpenAI’s Reboot and the Astra Model — firstadopter · 2026-08-27
- New TB-fn Benchmark Reveals Significant Drops in Terminal Model Rankings — abeirami · 2026-08-27
- Zhipu GLM-5.3-Flash Pricing Revealed: $0.15 Input — bindureddy · 2026-08-27
- Gemma 4 Release Delayed Due to Office Relocation — gajesh · 2026-08-27
- Claude's "not just X, this is Y" tic likely comes from post-training, not web data — burkov · 2026-08-27