Skip to content
Local AI Wizard
Your machine
Theme

GLM-4.5V

Z.ai · zai-org/GLM-4.5V

Weights license: MIT · code and components may use other terms

LMArena · vision1,153 ± 12#10 of 22 rated here · 2026-10-19
Memory needed~81 GBQ4 weights + working room, before the machine's reserve
Parameters107.7 BHub safetensors total
Repository updated2025-10-25A commit is not a release date

Quality

Reported by the publisher

The publisher's card states no benchmark result for this checkpoint (read 2026-10-25). not published on the card · read 2026-10-25

Quality × memory

No comparable quality × memory pair

This entry has no score on a benchmark that is drawn against planning memory.

Consider it for

Z.ai released GLM-4.5V on 2025-08-11: a vision-language model that answers about images, with 107.7B parameters on the Hugging Face count and the MIT license. Languages the publisher declares: zh, en.

Check first

License: commercial use allowed. At Q4 the weights load about 80.8 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick.

Runs on

Fast memory holds it 14

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 14

Within memory, outside the fast part 1

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

One memory tier short 2

The same machines with the next memory size up would hold it in fast memory.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Transformers · model card · Quick Start with Transformers
from transformers import AutoProcessor, Glm4vMoeForConditionalGeneration
import torch

MODEL_PATH = "zai-org/GLM-4.5V"
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "url": "https://upload.wikimedia.org/wikipedia/commons/f/fa/Grayscale_8bits_palette_sample_image.png"
            },
            {
                "type": "text",
                "text": "describe this image"
            }
        ],
    }
]
processor = AutoProcessor.from_pretrained(MODEL_PATH)
model = Glm4vMoeForConditionalGeneration.from_pretrained(
    pretrained_model_name_or_path=MODEL_PATH,
    torch_dtype="auto",
    device_map="auto",
)
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device)
inputs.pop("token_type_ids", None)
generated_ids = model.generate(**inputs, max_new_tokens=8192)
output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
print(output_text)
vLLM · model card · vLLM
vllm serve zai-org/GLM-4.5V \
     --tensor-parallel-size 4 \
     --tool-call-parser glm45 \
     --reasoning-parser glm45 \
     --enable-auto-tool-choice \
     --served-model-name glm-4.5v \
     --allowed-local-media-path / \
     --media-io-kwargs '{"video": {"num_frames": -1}}'
SGLang · model card · SGLang
python3 -m sglang.launch_server --model-path zai-org/GLM-4.5V \
     --tp-size 4 \
     --tool-call-parser glm45 \
     --reasoning-parser glm45 \
     --served-model-name glm-4.5v \
     --port 8000 \
     --host 0.0.0.0

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / source
zai-org/GLM-4.5V
Task
image-text-to-text
Architecture
Glm4vMoeForConditionalGeneration
Library in source
transformers
Weight license
MITzai-org/GLM-4.5V model card (Hugging Face) · read 2026-10-18source
Commercial use
Allowed MIT license text (SPDX) · read 2026-10-18license text
Languages
zh, enModel card metadata · read 2026-10-25source
Released
GLM-4.5V model card news: "2025/08/11: We released GLM-4.5V" (Hugging Face) · read 2026-10-18source
Every stored field13 fields
Revision checked
ed47433b37111465ec527affaaddceff371bca04
Architecture
Glm4vMoeForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Declared base models
zai-org/GLM-4.5-Air-Base
Formats
transformers, safetensors
Access
Open download
Publisher kind
Official
Hub parameter count
107,710,933,120safetensors.total
Repository created
2025-08-10creation is not the model's release
Repository updated
2025-10-25a commit is not a release date
Hub downloads (30 days) · likes
24,483 · 726this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-18. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.