gpuos

Chat · Pro plan

Run GLM-4 32B 0414 on your own GPU

Zhipu's GLM-4 32B (0414) is a dense chat model under the MIT license, strong at function calling, code and structured output, and slightly lighter than Qwen3 32B in VRAM.

With gpuos, GLM-4 32B 0414 runs on Ollama at Q4_K_M on your machine and is served as glm-4-32b through one OpenAI-compatible endpoint, with API keys, quotas and usage metering.

Parameters
32B dense
Quantization
Q4_K_M
VRAM (4–8K ctx)
≈ 20.5 GB
Context window
32K tokens
License
MIT
Engine
Ollama
Ollama tag
hf.co/bartowski/THUDM_GLM-…
API
/v1/chat/completions

What GLM-4 32B 0414 is good at

Which GPUs can run GLM-4 32B 0414?

Catalog estimate at Q4_K_M, not a measured benchmark. Chat estimates assume a short context; embedding memory depends on input and batch size. More in how much VRAM an LLM needs.

Check this estimate against your GPU with the VRAM calculator

Call GLM-4 32B 0414 with the OpenAI SDK

Same SDKs, same request format. Only the base URL, the key and the model name change. Setup for LangChain, Continue, Open WebUI and more is in integrations.

Python
from openai import OpenAI

client = OpenAI(base_url="https://gpuos.si/v1", api_key="gpuos_key_…")
stream = client.chat.completions.create(
    model="glm-4-32b",
    messages=[{"role": "user", "content": "Summarize our refund policy."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")
Node.js
import OpenAI from "openai"

const client = new OpenAI({ baseURL: "https://gpuos.si/v1", apiKey: process.env.GPUOS_API_KEY })
const reply = await client.chat.completions.create({
  model: "glm-4-32b",
  messages: [{ role: "user", content: "Summarize our refund policy." }],
})
console.log(reply.choices[0].message.content)
curl
curl https://gpuos.si/v1/chat/completions \
  -H "Authorization: Bearer $GPUOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-4-32b", "messages": [{"role": "user", "content": "Hello"}]}'

Questions

How much VRAM does GLM-4 32B 0414 need?
About 20.5 GB at Q4_K_M with a short context (4–8K tokens). The smallest common GPU that fits it is the RTX 3090 / 4090 24 GB. Longer contexts and more concurrent requests need extra headroom for the KV cache.
Can I use GLM-4 32B 0414 commercially?
Yes. GLM-4 32B 0414 is released under the MIT license, which allows commercial use.
Is GLM-4 32B 0414 compatible with the OpenAI API?
Yes. Through gpuos, GLM-4 32B 0414 is served at /v1/chat/completions with the model id "glm-4-32b", so the official OpenAI SDKs, LangChain and LlamaIndex work by changing the base URL and the API key.
Which gpuos plan includes GLM-4 32B 0414?
GLM-4 32B 0414 is part of the full catalog on the Pro plan, $29 per GPU per month.

Related models

Plan your GLM-4 32B 0414 deployment with gpuOS

Join early access for onboarding, or read the quickstart to evaluate the Community workflow on your own GPU.

Join early accessRead the quickstart