PulseAugur
EN
LIVE 18:12:55
Deutsch(DE) Tencent stellt Hy3-FP8 vor: die FP8-Quantisierung des 295B-Parameter-MoE-Modells mit 21B aktiven Parametern. Apache-2.0-Lizenz, 256K Kontextfenster und native v

Tencent releases Hy3-FP8 model with 21B active parameters

By PulseAugur Editorial · [2 sources] ·

Tencent has released Hy3-FP8, an FP8-quantized version of its 295 billion parameter MoE model, which utilizes 21 billion active parameters. This model is released under the Apache 2.0 license and features a 256K context window. The implementation is designed to reduce VRAM consumption for operation, with native vLLM and SGLang integration. AI

IMPACT This release offers a more efficient way to run large MoE models, potentially lowering the barrier for deploying advanced AI capabilities.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Tencent releases Hy3-FP8 model with 21B active parameters

COVERAGE [2]

  1. Mastodon — mastodon.social TIER_1 Deutsch(DE) · aisyndicate ·

    Tencent Hy3 is an Apache 2.0 licensed MoE model with 295B total parameters and 21B active parameters. It uses a 3.8B MTP layer and offers 256K context

    Tencent Hy3 ist ein Apache-2.0-lizenziertes MoE-Modell mit 295B Gesamtparametern und 21B aktiven Parametern. Es nutzt eine 3,8B MTP-Schicht und bietet 256K Kontext. Serving über vLLM oder SGLang mit OpenAI-API, FP8-Variante verfügbar. https:// huggingface.co/tencent/Hy3 # KI # AI…

    LINKS huggingface.co/…/Hy3
  2. Mastodon — mastodon.social TIER_1 Deutsch(DE) · aisyndicate ·

    Tencent introduces Hy3-FP8: FP8 quantization of the 295B parameter MoE model with 21B active parameters. Apache-2.0 license, 256K context window, and native v

    Tencent stellt Hy3-FP8 vor: die FP8-Quantisierung des 295B-Parameter-MoE-Modells mit 21B aktiven Parametern. Apache-2.0-Lizenz, 256K Kontextfenster und native vLLM-/SGLang-Anbindung reduzieren den VRAM-Verbrauch für den Betrieb. https:// huggingface.co/tencent/Hy3-FP8 # KI # AI #…

    LINKS huggingface.co/…/Hy3-FP8

RELATED ENTITIES

RELATED TOPICS