@AdinaYakup: Hy-MT2 New translation model family from @TencentHunyuan 1.8B / 7B / 30B-A3B MoE Supports 33 languages 1.8B > 440MB wit…
Summary
Tencent Hunyuan released Hy-MT2, a family of translation models up to 30B parameters with MoE, supporting 33 languages and quantized for on-device use.
View Cached Full Text
Cached at: 05/22/26, 03:53 AM
Hy-MT2 🔥 New translation model family from @TencentHunyuan
✨ 1.8B / 7B / 30B-A3B MoE ✨ Supports 33 languages ✨ 1.8B > 440MB with 1.25-bit quantization ✨ Runs on device with faster inference ✨ 1.8B outperforms some commercial APIs https://t.co/Ep7gL8wedk
Similar Articles
Running Vision Qwen 3.8 27B on a 16GB Card, the config (45tks).
User shares configuration for running Vision Qwen 3.8 27B model on a 16GB GPU using beellama, achieving 45 tokens per second decode and 85K context.
@jakevin7: Holy shit, that's impressive! DeepSeek, is this really just a minor tweak to a small version??? V4.1 Flash made a ton o…
DeepSeek V4.1 Flash introduces architectural improvements for long context handling, including causal encoder-decoder, CSA2, hierarchical sparse indexer, and quantization, leading to major memory and compute optimizations.
SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers
The paper presents a data selection method for terminology-aware translation that trains only on hard examples where the model's output contradicts the glossary, achieving improved term accuracy, and describes the BSC system submission to the WMT26 Terminology Shared Task.
SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia
SEA-SpeechBench is the first large-scale multitask benchmark for evaluating speech understanding in 11 Southeast Asian languages, highlighting performance gaps in current models.
BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models
BuzzASR is a collection of language-specialized Whisper models for automatic speech recognition in 102 languages, outperforming Whisper-large-v3 on 77 languages with significant improvements in error rates and compression efficiency.