GLM 4.6

zai-org · released 2025-09-30 · mit license

GLM-4.6 is Z.ai's 357B-parameter (32B active) MoE (Sept 2025, MIT) with a 200K context; it scores 30 on the Artificial Analysis Intelligence Index and reports 82.8% on LiveCodeBench v6. A leading open-source coding model at launch.

Key specs

TypeLocal open-weight
Parameters356.79B total · MoE, — active
Architectureglm4_moe
Context window203K tokens
Knowledge cutoff2025-03-31
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond
SWE-bench Verified
AIME
MMLU-Pro
BFCL v3 (tool use)
Composite score
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M208.4 GB206.9 GB203K

Strengths & weaknesses

Strengths: Strong real-world coding in agent frameworks (Claude Code, Cline, Roo); 200K context, ~30% better token efficiency than GLM-4.5; MIT license

Weaknesses: Trails Claude Sonnet 4.5 in pure coding; Text-only