GLM-5-FP8
By zai-org. 753.9 billion parameters, a context window of 202,752 tokens and the licence mit.
Facts
- Released
- 2026-02-11 the day the repository was first published on Hugging Face Hugging Face, read
- Licence
- mit the licence the model card declares Hugging Face, read
- Open weights
- Yes the weights are published in this Hugging Face repository Hugging Face, read
- Parameters
- 753.9 billion counted from the safetensors weight files Hugging Face, read
- Active parameters
- 51.8 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
- Knowledge cutoff
- Unknown
- Context window
- 202,752 tokens the maximum position embeddings in the model configuration model configuration, read
- Longest output
- Unknown
- Tool calling
- Unknown
- Structured output
- Unknown
- Reasoning controls
- Unknown
- Inputs and outputs
- text in, text out Hugging Face, read
- Good for
- No source names a use.
Prices
| Provider | Input | Output | Context | As of | Source |
|---|---|---|---|---|---|
| GMI Cloud direct | 0.600 USD | 1.92 USD | 202,752 | older than 30 days; check the provider | models.dev, read |
Run it on your own hardware
Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.
| Quantization | Weights | Memory at 8,192 tokens | Memory at 32,768 tokens |
|---|---|---|---|
| F16 estimate | 1,404 GiB | 1,476 GiB | 1,478 GiB |
| Q8_0 estimate | 746 GiB | 785 GiB | 787 GiB |
| Q4_0 estimate | 395 GiB | 416 GiB | 418 GiB |
Start it with a local runtime
Use it from your harness
Set up for GMI Cloud with the model zai-org/GLM-5-FP8. Each endpoint page has the same setup for its own address.
OpenCode
Put this in opencode.json in your project folder:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"gmicloud": {
"npm": "@ai-sdk/openai-compatible",
"name": "GMI Cloud",
"options": {
"baseURL": "https://api.gmi-serving.com/v1",
"apiKey": "{env:GMICLOUD_API_KEY}"
},
"models": {
"zai-org/GLM-5-FP8": {
"name": "GLM-5-FP8"
}
}
}
}
}- OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.
From OpenCode documentation, read .
Pi
Put this in ~/.pi/agent/models.json:
{
"providers": {
"gmicloud": {
"baseUrl": "https://api.gmi-serving.com/v1",
"api": "openai-completions",
"apiKey": "$GMICLOUD_API_KEY",
"models": [
{
"id": "zai-org/GLM-5-FP8"
}
]
}
}
}- The apiKey field can name an environment variable as $NAME.
From Pi documentation, read .
Codex
Codex speaks only the Responses API, and GMI Cloud documents no Responses address. A gateway that offers one can sit in between.
- Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.
From Codex documentation, read .
Claude Code
Claude Code sends Anthropic Messages requests, and GMI Cloud documents no such address. A gateway that translates to that API can sit in between.
- Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.
From Claude Code documentation, read .
Published results
These are results other people published. Baltor did not run them and does not rank models by them.
- Results the maker published on the model card published by zai-org Hugging Face, read
Sources of this page
Paid links
No link in this directory is a paid link or an ad, and no listing is paid for. The order and the contents of every list come from the sources named on this page.