AION
Modelofficial release

nvidia/GLM-5.3-Flash-NVFP4

Parameters169B
Context1M
Input → outputimage + text → text
Licensemit
PrecisionU8 · nvfp4
ArchitectureGlm5NextForConditionalGeneration
ReleasedSep 2, 2026
Downloads92.9K

Based on zai-org/GLM-5.3-Flash

This release in the news

No coverage of this exact release yet.

Recent news about GLM

  1. Oct 8, 2026 · Research paper
    Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models
  2. Oct 8, 2026 · Research paper
    REMORY: Learning Residual Memory for Context Compaction
  3. Oct 8, 2026 · Research paper
    QUILT: Rethinking Sparse-Attention Prefill through Shared Query Execution
  4. Oct 7, 2026 · Research paper
    How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense
  5. Oct 6, 2026 · Research paper
    Socio-Foundation: A Model for Generalizable Individual Behavior Simulation via Hierarchical Capability Distillation
  6. Oct 6, 2026 · Research paper
    MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory
  7. Oct 6, 2026 · Opinion / analysis
    The Cyber Risk Discourse is Broken
  8. Oct 6, 2026 · Research paper
    Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT