Bonus: Top up now and we'll double your first deposit — get x2 credits instantly.

GLM-4 9B Chat 1M: Self-Hosting & Deployment Guide

GLM-4 9B Chat 1M is a compact open-weight chat model with a one-million-token context window.

What is GLM-4 9B Chat 1M?

GLM-4 9B Chat 1M is a compact open-weight chat model with a one-million-token context window, published by Z.ai with open weights at zai-org/glm-4-9b-chat-1m. LLM API does not route this model today, so there is no endpoint or code sample for it here. What this page does give you is the self-hosting picture: published weight sizes, the VRAM each quantisation needs and the commands to serve it yourself. Every figure is read from the public repository and refreshed weekly.

How to run GLM-4 9B Chat 1M yourself

Open weights (other), 9.5B parameters. Below: how much memory the weights need at each quantization, which hardware fits them, and the commands to serve it.

GLM-4 9B Chat 1M VRAM requirements

Precision / quantizationWeightsFigureSource
BF16 (full precision)19 GBEstimate9.5B params × 2 bytes
MLX 4-bit5.3 GBFile sizemlx-community/glm-4-9b-chat-1m-4bit
GGUF Q8_010.1 GBFile sizebartowski/glm-4-9b-chat-1m-GGUF
GGUF Q4_K_M6.3 GBFile sizebartowski/glm-4-9b-chat-1m-GGUF
GGUF Q2_K4 GBFile sizebartowski/glm-4-9b-chat-1m-GGUF

File size = actual download size on Hugging Face. Estimate = parameter count × bytes per weight. Weights only — the KV cache for long contexts needs extra memory; the fit tables below add 15% headroom as a rule of thumb.

GPU requirements: deploy GLM-4 9B Chat 1M on your hardware

HardwareBF16 (full precision)MLX 4-bitGGUF Q8_0GGUF Q4_K_MGGUF Q2_K
NVIDIA H200141 GB
NVIDIA H10080 GB
NVIDIA A100 80GB80 GB
NVIDIA L40S48 GB

GPUs needed per variant.

HardwareGGUF Q8_0GGUF Q4_K_MGGUF Q2_K
RTX 509032 GB
RTX 409024 GB
RTX 309024 GB

GGUF via llama.cpp; more cards or CPU offload for larger files.

HardwareGGUF Q8_0GGUF Q4_K_MGGUF Q2_KMLX 4-bit
Mac, 512 GBM3 UltraFitsFitsFitsFits
Mac, 192 GBM2 UltraFitsFitsFitsFits
Mac, 128 GBM4 Max / M3 MaxFitsFitsFitsFits
Mac, 64 GBM4 Pro / MaxFitsFitsFitsFits

Assumes ~75% of unified memory is usable by the GPU.

HardwareBF16 (full precision)MLX 4-bitGGUF Q8_0GGUF Q4_K_MGGUF Q2_K
AWS p5.48xlarge8× H100 · 640 GBFitsFitsFitsFitsFits
AWS p4de.24xlarge8× A100 80GB · 640 GBFitsFitsFitsFitsFits
AWS g6e.12xlarge4× L40S · 192 GBFitsFitsFitsFitsFits
Google Cloud a3-highgpu-8g8× H100 · 640 GBFitsFitsFitsFitsFits
Azure ND H100 v58× H100 · 640 GBFitsFitsFitsFitsFits

Whole-instance GPU memory; public instance specs.

Not on LLM.API yet

We do not route this model through our API at the moment. Browse the models you can call today — most workloads have a close match already live.

Not available on LLM API yet

We do not route this model through our API at the moment, so there is no endpoint or code snippet for it yet. Browse the models you can call today — most workloads have a close match already live.

Browse available models

Why run GLM-4 9B Chat 1M on LLM.API?

  • Unified AI Routing

    Reach GLM-4 9B Chat 1M and sibling models through one OpenAI-compatible endpoint.

  • Cost Control

    Production: Compare provider price points and keep spend visible as you scale GLM-4 9B Chat 1M.

  • Reliability Layer

    Retry and route across configured providers when a single upstream blips.

  • Observability

    Trace prompts, tokens, and errors for GLM-4 9B Chat 1M alongside the rest of your stack.

  • Drop-in SDKs

    Keep using familiar OpenAI client patterns with base URL https://api.llmapi.ai/v1.

  • Model Breadth

    Swap GLM-4 9B Chat 1M for chat, media, or embedding alternatives without rewriting auth.

When to Use — When NOT to Use

Get one key to every model

Swap your API key. Keep your code.