Language

GLM-5 (MoE)

Z.ai GLM-5 — 744B total parameter MoE, 40B active, trained on 28.5T tokens. Routes each token to 8 of 256 experts plus 1 shared across 75 MoE layers, with DeepSeek Sparse Attention over a 198K context. Unsloth dynamic UD-Q4_K_XL GGUF (sharded).

MITSource verified

Specification

Model ID

glm-5

Family

glm

Modality

Language

Parameters

744B (MoE, 40B active)

Context

202,752 tokens

Quantization

UD-Q4_K_XL

Weights

372.5 GB

Minimum RAM

256 GB

Source

Weights and provenance.

Repository

unsloth/GLM-5-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

# Serve it
tenzro model serve glm-5

# 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"}]}'

Same family

GLM-5.1 (MoE)

744B (MoE, 40B active)

GLM-5.2 (MoE, MTP)

753B (MoE, 40B active)

GLM-4 9B Chat

← All models