This model requires you to accept the MIT license terms before download.
Description
GLM-4.1V-9B-Thinking — vision-language reasoning model (image+text → text with <think> traces). Dynamic-resolution vision, first VLM on NeuroBrix; validated 4/4 execution modes token-identical.
Tags
At a glance
| Kind | vision-language model |
|---|---|
| Precision | bfloat16 |
| Container size | 19.2 GiB |
| Weights inside | 19.2 GiB |
| Components | 3 |
| Licence | MIT |
What is inside the container
A .nbx container packs every part of GLM-4.1V-9B-Thinking — 3 components with weights, graphs and runtime settings — so one file is all the runtime needs.
| Component | Blocks | Layers | Weights |
|---|---|---|---|
| model.language_model | 0 | 40 | 16.4 GiB |
| model.visual | 0 | — | 1.7 GiB |
| lm_head | 0 | — | 1.2 GiB |
Default settings
The values the container ships with. They apply when you do not pass your own.
- Max length
- 65536
- Temperature
- 0.8
- Top-p
- 0.6
- Top-k
- 2
Memory needed
The weights of GLM-4.1V-9B-Thinking take 19.2 GiB in bfloat16. That is the floor for the memory the runtime has to place, spread over the devices it finds; activations come on top and grow with the size and length you ask for. A measured peak per device class is not published for this model yet.
Verify what you downloaded
Every download carries its SHA-256, and the file endpoint sends it in the X-NBX-SHA256 header. The container is 19.2 GiB (20,589,371,153 bytes).
$ sha256sum GLM-4.1V-9B-Thinking.nbx
eaa8416f2bc90e28a787abce694be0ca074b68a0c91613f2a8babf6915573543
Questions
What is GLM-4.1V-9B-Thinking?
A vision-language model by zai-org, distributed as a bfloat16 .nbx container and licensed MIT.
How big is the download?
19.2 GiB, of which 19.2 GiB are weights.
How do I run it?
Install the runtime from the download page, then use the commands under “CLI Usage” below: neurobrix import zai-org/GLM-4.1V-9B-Thinking, then neurobrix serve --model GLM-4.1V-9B-Thinking.
CLI Usage
$ neurobrix import zai-org/GLM-4.1V-9B-Thinking
$ neurobrix serve --model GLM-4.1V-9B-Thinking
$ neurobrix run --prompt "your prompt here"
$ neurobrix stop