GLM-4 9B

Zhipu AI · GLM family · released 2024-06-05 · GLM license

GLM-4 9B by Zhipu AI — 9B open-weight local LLM. License: GLM. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopsome.com.

Key specs

TypeLocal open-weight
Parameters9B total
Architecture
Context window131K tokens
Knowledge cutoff
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond38%
SWE-bench Verified22%
AIME40%
MMLU-Pro58%
BFCL v3 (tool use)72%
Composite score13.66
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M7 GB6 GB12 GB131K