Language

GLM-5.1 (MoE)

Z.ai GLM-5.1 — next-generation flagship for agentic engineering, class-leading on SWE-Bench Pro; 744B total / 40B active, 8 of 256 experts plus 1 shared across 75 MoE layers; 198K context. `glm_moe_dsa` architecture with Dynamic Sparse Attention.

MITSource verified

Specification

Model ID

glm-5.1

Family

glm

Modality

Language

Parameters

744B (MoE, 40B active)

Context

202,752 tokens

Quantization

UD-Q4_K_M

Weights

372.5 GB

Minimum RAM

256 GB

Source

Weights and provenance.

Repository

unsloth/GLM-5.1-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-5.1

# Serve it
tenzro model serve glm-5.1

# 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-5.1"}]}'

Same family

GLM-5 (MoE)

744B (MoE, 40B active)

GLM-5.2 (MoE, MTP)

753B (MoE, 40B active)

GLM-4 9B Chat

← All models