Modelofficial release

zai-org/GLM-4.6-FP8

Parameters358B
Context198K
Input → outputtext → text
Licensemit
PrecisionF8_E4M3 · fp8
ArchitectureGlm4MoeForCausalLM
ReleasedSep 29, 2025
Downloads6.8K

Other sizes and formats in the family

ModelParamsPrecisionDownloads
zai-org/GLM-4.6357BBF1617.6K

Compare side by side →

This release in the news

No coverage of this exact release yet.

Recent news about GLM

  1. Oct 11, 2026 · Opinion / analysis
    "Strata" for GLM5.3 Flash is here for some! Project Maya
  2. Oct 11, 2026 · Opinion / analysis
    vllm-ascend updates (GLM5.3-flash) on dual 310p Ascend cards
  3. Oct 8, 2026 · Research paper
    Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models
  4. Oct 8, 2026 · Research paper
    REMORY: Learning Residual Memory for Context Compaction
  5. Oct 8, 2026 · Research paper
    QUILT: Rethinking Sparse-Attention Prefill through Shared Query Execution
  6. Oct 7, 2026 · Research paper
    How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense
  7. Oct 6, 2026 · Research paper
    Socio-Foundation: A Model for Generalizable Individual Behavior Simulation via Hierarchical Capability Distillation
  8. Oct 6, 2026 · Research paper
    MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory