Optimizing GLM4-MoE for Production: 65% Faster TTFT with SGLang
As the state-of-the-art GLM 4.7 model continues to lead in coding performance, Novita AI remains committed to delivering a reliable, efficient, and production-grade GLM service to
Filter posts by category
Deploy GLM-Image on Novita AI GPU Instance: Complete Setup Guide
Deploy GLM-Image on Novita AI GPU instances in minutes. Step-by-step guide to running this hybrid autoregressive-diffusion model.
GLM-4.7 VRAM Requirements Explained: Run Locally, on Novita GPU Cloud, or via API
Run GLM-4.7 without hardware pain: compare local, Novita GPU Cloud, and Novita API paths for reasoning, coding, and long-context workloads.
GLM-4.7 vs Claude Sonnet 4.5: Which One Should You Choose?
GLM-4.7 vs Claude Sonnet 4.5: benchmark strengths, speed/latency, and pricing—where each wins, and why GLM often costs far less.
Use GLM-4.7 in Claude Code: Cost-Effective Agentic Coding via Novita AI
Integrate GLM-4.7 with Claude Code via Novita AI’s Anthropic-compatible endpoint. Setup steps, benchmarks, and why it’s a strong Claude alternative.
How To Integrate Novita AI LLM API With Kilo Code
A complete guide to integrating all models from Novita AI using the Kilo Code plugin in VS Code.
Deploy NVIDIA Nemotron Speech ASR Model on Novita AI GPU Instance
Deploy NVIDIA Nemotron Speech ASR model on Novita AI GPU Instance for sub-100ms latency. Step-by-step guide with cache-aware streaming for 3x throughput.
How to Deploy and Host Claude Agent SDK with Novita Sandbox
Learn how to deploy Claude Agent SDK in production using Novita Sandbox, an E2B-compatible cloud execution environment.
How to Build a Chrome Plugin Using Novita AI Sandbox
Learn how to build a Chrome extension with an AI assistant that follows you across pages, explains code, and runs it safely in a sandbox.
DeepSeek V3.2 VRAM: Is Local Deployment Still Practical Today
Explore DeepSeek V3.2 VRAM requirements and its impact on hardware costs and performance in real-world applications.
Building a Coding Agent with Novita’s Agent Sandbox
Learn how to use Novita’s LLMs and Agent Sandbox to build a secure environment where your agent can code, build, and experiment without the risk of “breaking anything.”
ERNIE-4.5-VL-A3B VRAM Requirements: Run Multimodal Models at Lower Cost
Explore the challenges of deploying ERNIE-4.5-VL-A3B VRA and learn about hardware requirements and cost-efficient alternatives.
How to Access GLM-4.6V and Build Reliable Multimodal Agents？
Discover how to access GLM-4.6V for improved multimodal workflows and enhanced image and document interpretation.
GLM 4.6V VRAM Requirements: Choosing GPUs for Multimodal Inference
Explore the GLM 4.6V VRAM requirements for deploying advanced vision-language models effectively and efficiently.