What GPU do I need to run zai-org/GLM-4.5V?

What GLM-4.5V is

GLM-4.5V is a 108B-parameter vision-language model published by Z.ai (Zhipu) on Hugging Face. It is released under MIT.

License note: permissive: allows commercial use, modification and redistribution. Facts in this section are sourced from GLM-4.5V's Hugging Face model card, not benchmarked by Aquanode.

What it's used for

• Image understanding and captioning
• Visual question answering
• Document/OCR-style reading

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

GLM-4.5V: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

Grouped-query attention: every layer caches keys and values for a few shared KV heads. Cached per token: 188,416 bytes at 16-bit.

Computed from the layer, head and window counts in the model's own configuration (zai-org/GLM-4.5V), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

GLM-4.5V: common questions

How to run GLM-4.5V

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}}'

llama-server -hf mradermacher/GLM-4.5V-GGUF

Deploy GLM-4.5V on Aquanode

Aquanode has no one-click deploy template for GLM-4.5V; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.

1. Launch a bare GPU pod sized to the requirement above (6× RTX A6000 or larger).
2. Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
3. Run the command and connect to the resulting endpoint.

Launch a GPU pod

More GLM-4.5 models

• GLM-4.5-Air (110.5B, BF16)
• GLM-4.5-Air-Base (110.5B, BF16)
• GLM-4.5-Air-FP8 (110.5B, F8_E4M3)
• GLM-4.6 (356.8B, BF16)
• GLM-4.5 (358.3B, BF16)

All 10 GLM-4.5 models: VRAM and GPU requirements

Lineage

Based on GLM-4.5-Air-Base.

Alternatives at this size

Other models for image-text-to-text within about a third of GLM-4.5V's 107.7B parameters, from other model lines.

• Qwen3.5-122B-A10B (125.1B, BF16)
• Llama-4-Scout-17B-16E-Instruct (108.6B, BF16)
• InternVL3-78B (78.4B, BF16)

More on GLM-4.5V

• Fits on a 288 GB GPU at BF16: every model that fits in 288 GB.

• Fits on a 141 GB GPU at FP8: every model that fits in 141 GB.

• Fits on an 80 GB GPU at INT4: every model that fits in 80 GB.

• Best vision-language models: how GLM-4.5V ranks against the rest.

• How to run GLM-4.5 and how to fine-tune GLM-4.5.