Latest Content
GLM 4.7 icon

GLM 4.7

NVIDIA
GLM 4.7 is a Mixture-of-Experts (MoE) large language model developed by Zhipu AI, designed for advanced coding, reasoning, and agent-driven development workflows. The model features 358B total parameters, built on a 92-layer transformer architecture with 96 attention heads and a 5,120 hidden size, utilizing 160 routed experts with 8 experts activated per token to efficiently scale performance for complex tasks. It supports ~202K token context window and introduces Interleaved Thinking, Preserved Thinking, and Turn-level Thinking capabilities for more stable and controllable complex task execution.
TypeMoE LLM
CapabilitiesText Generation, Instruction Following, Reasoning, Mathematical Reasoning+5 more
Release Date22 December, 2025
Links
Blog|HF Model Card
LicenseMIT

Inference Instructions

Deploy and run this model on NVIDIA B200 GPUs using the command below. Copy the command to get started with inference.

CONSOLE
docker run -it --rm 
 --runtime=nvidia 
 --gpus all 
 --ipc=host 
 --shm-size=128g 
 -p 8000:8000 
 -v ~/.cache/huggingface:/root/.cache/huggingface 
 -e VLLM_FLOAT32_MATMUL_PRECISION=high 
 -e HF_TOKEN='YOUR_HF_TOKEN' 
 -e LD_LIBRARY_PATH='/usr/local/nvidia/lib64:/usr/local/nvidia/lib:/usr/lib/x86_64-linux-gnu' 
 vllm/vllm-openai:v0.15.0-cu130 
 zai-org/GLM-4.7 
  --tensor-parallel-size 8 
 --max-model-len auto 
  --gpu-memory-utilization 0.95 
 --max-num-batched-tokens 65536 
 --tool-call-parser glm47 
 --reasoning-parser glm45 
 --enable-auto-tool-choice 
 --max-num-seqs 1024 
 --disable-log-requests 
 --trust-remote-code

Model Benchmarks

Each model was tested with a fixed input size and total token volume while increasing concurrency to measure serving performance under load.

ITL vs Concurrency

Time to First Token

Throughput Scaling

Total Tokens/sec vs Avg TTFT

Vultr Cloud GPU

NVIDIA HGX B200

Deploy NVIDIA B200 on Vultr Cloud GPU

Deploy NVIDIA B200 instancesContact Sales