Tenzro
Language

GLM-5.2 (MoE, MTP)

Z.ai GLM-5.2 — 753B total parameter MoE flagship, 40B active, routing each token to 8 of 256 experts plus 1 shared across 75 MoE layers. Solid 1M-token context with IndexShare sparse-attention (2.9× per-token FLOP reduction at 1M). Improved Multi-Token-Prediction layer increases speculative-decoding accept rate by ~20% over GLM-5.1.
MITSource verified
Specification
Model ID
glm-5.2
Family
glm
Modality
Language
Parameters
753B (MoE, 40B active)
Context
1,048,576 tokens
Quantization
UD-Q4_K_XL
Weights
381.8 GB
Minimum RAM
256 GB
Source

Weights and provenance.

Repository
unsloth/GLM-5.2-GGUF
Registry license
MIT
Source license
mit
Access
Open — weights fetch without accepting additional terms.
Serve it
# Pull the weights onto a node
tenzro model download glm-5.2

# Serve it
tenzro model serve glm-5.2

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"glm-5.2"}]}'
Same family
GLM-5 (MoE)
744B (MoE, 40B active)
GLM-5.1 (MoE)
744B (MoE, 40B active)
GLM-4 9B Chat
9B
← All models