← Back to Models

glm-4.7-flash

zai-org/glm-4.7-flash

View on HuggingFace
Publisher
zai-org
Architecture
glm4_moe_lite(sparse)
Parameters
30B
Quantization
6bit (6.0 bpw)
Format
mlx
Max Context
203k tokens
Type
llm
File Size
22.68 GB
Est. RAM
24.2 GB
Est. VRAM
24.2 GB
Capabilities
trained_for_tool_use

Benchmark Results

Compare Models