GLM-4.5
Zhipu AI / Z.ai · Mixture-of-Experts (MoE) · License: MIT
Zhipu's flagship reasoning-and-agent-focused model, released under the fully permissive MIT license alongside a smaller 106B "Air" variant.
Memory requirement — the visual calculator
In real deployments, memory needs also depend on numeric precision (e.g. FP16 vs INT8 vs INT4), which changes bytes-per-parameter. This store uses a simplified, transparent formula so beginners can follow the logic: (parameters in billions × 1 GB) + 20% overhead for the runtime, active requests, and context memory.
Calculation: 355B parameters × 1 GB = 355 GB, plus 20% (71.0 GB) = 426.0 GB total The dedicated memory built into the graphics card. An AI model's entire set of "weights" (its learned parameters) must fit into this memory before the card can run it. If a model needs more VRAM than one card has, you need multiple cards working together, or a card with more memory. needed. Note: even though only 32B parameters ( A model design where only a fraction of the model's parameters ("active parameters") are used to process any single piece of text, even though the full model is much larger. This makes the model faster to run than its total size suggests, but you still need enough memory to hold the entire model, not just the active part. ) are active per token, the full 355B must still be loaded into memory.
Leaderboard
Added to the LMArena text leaderboard in August 2025.