RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Eruo Fredoline
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
  • Suggest a feature
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
← /pulse/hunyuan-3-apache-2-release
ADVISORYMODEL RELEASE·2026-07-10

Tencent Hunyuan 3.0 goes Apache 2.0 - EU/UK exclusion dropped

▼ WHAT HAPPENED

Tencent officially released Hunyuan 3.0 (295B MoE, 21B active) on 2026-07-06 under Apache 2.0, with an official FP8 quantization aimed at local deployment. The license reversal matters as much as the weights: the April preview excluded EU, UK, and South Korea users, and the Apache 2.0 release removes that restriction - a material change in who can legally run it locally. At 295B total parameters even FP8 needs several hundred GB of memory, so this is multi-GPU server or top-spec unified-memory territory (think 512GB Mac Studio M3 Ultra class), not consumer cards.

▼ OPERATOR ANGLE

If you skipped the Hunyuan preview for license reasons - especially in the EU or UK - that blocker is gone. Realistically this model is for large unified-memory rigs and multi-GPU servers; check the official FP8 build's memory requirements against your hardware before downloading hundreds of GB.
SOURCE: https://venturebeat.com/technology/tencents-apache-licensed-hy3-takes-on-glm-5-2-at-half-the-size-and-wins-everywhere-except-coding[BLOG]

▼ ENTITIES REFERENCED

HARDWAREApple Mac Studio (M3 Ultra)TOOLvLLM
[pulse item] · runlocalai.co/pulse/hunyuan-3-apache-2-release