The Open-Source AI Stack
RSS
All models

Models · glm-4

GLM-4.5

Open Zhipu AI · 2025-07-28 · MIT

Zhipu's first ARC-focused flagship (agentic, reasoning, coding), released July 28 2025 as 355B total / 32B active MoE under MIT. 23T-token pretraining run. Hybrid thinking / non-thinking modes. GLM-4.5-Air (106B / 12B) released alongside. Zhipu reports 90.6 percent tool-calling success vs Claude 4 Sonnet's 89.5 percent.

Architecture

tokens in Embedding vocab not disclosed × N layers Attention (not disclosed) Position encoding not disclosed context 128,000 tokens MoE Router ? experts total · ? active per token Output projection tokens out
Schema-generated from data/models.yaml. Every label is auditable against the model's sources.

Specs

Architecture
moe
Total params
355B
Active params
32B
Context window
128K tokens
Attention
unknown
Position encoding
unknown
Pretraining tokens
23.0T
Post-training
sft, rlhf
OSI-approved
yes
Data released
no
Training code
not released

Benchmarks

Each score carries the date it was published; we never infer or interpolate missing scores.

Code

SWE-Bench Verified 64.2 as of 2025-07-28 source ↗

Math

AIME 2024 91.0 as of 2025-07-28 source ↗

Available quantizations

GGUF llama.cpp's container; the common local format, k-quants from Q2 to Q8. runs on llama.cpp, Ollama
AWQ Activation-aware 4-bit weight quantization for GPU serving. runs on vLLM, SGLang
GPTQ Post-training 4-bit weight quantization for GPU serving. runs on vLLM, SGLang, Transformers
EXL2 ExLlamaV2's variable-bitrate format for consumer GPUs. runs on ExLlamaV2
MLX Apple MLX 4/8-bit layout for Apple silicon. runs on Apple MLX

Verified via the Hugging Face model tree ↗. Community quantizations change over time; the families shown are those with published weights at audit time.

Notable innovations

  • · MIT-licensed 355B MoE
  • · Hybrid thinking / non-thinking modes
  • · Multi-Token Prediction layers with speculative decoding
  • · 23T-token pretraining

Lineage

First Zhipu ARC flagship; 355B MoE under MIT. New pretrain, architectural break from the dense GLM-4 9B series.

Derivatives

Sources