What GPU do I need to run zai-org/GLM-5.1?
A 754B (MoE) language model for chat and instruction-following. 753.9B parameters, published in BF16. View on Hugging Face
GLM-5.1 is published by zai-org on Hugging Face, with 87,580 downloads and 1,841 likes to date. It's a GlmMoeDsaForCausalLM model built for text-generation, published natively in BF16.
What GLM-5.1 is
GLM-5.1 is a 754B-parameter mixture-of-experts 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-5.1's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Chat assistants
- Instruction following
- Synthetic data generation
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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 1404.2 GB | 1685.0 GB | No capable live offer found | – | – |
| FP8 (quantized) | 702.1 GB | 842.5 GB | AMD MI300X | 5 | $13.14/hr |
| INT4 (quantized) | 351.0 GB | 421.3 GB | A100 | 6 | $6.93/hr |
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-5.1: 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.
Multi-head latent attention: every layer caches one compressed latent per token. Cached per token: 89,856 bytes at 16-bit.
| Context | KV cache, one sequence |
|---|---|
| 4K | 0.34 GB |
| 32K | 2.7 GB |
| 128K | 11.0 GB |
| 198K (model maximum) | 17.0 GB |
Computed from the layer, head and window counts in the model's own configuration (zai-org/GLM-5.1), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.
GLM-5.1: common questions
Can GLM-5.1 run on a single GPU?
Not on a desktop card. At BF16 it needs 1685.0 GB of VRAM, more than a single 32 GB desktop card holds. No card currently listed on the marketplace both supports BF16 and has enough VRAM for it, so how many it would take is not something this page can answer today.
How to run GLM-5.1
Run GLM-5.1 with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve zai-org/GLM-5.1 --tensor-parallel-size 1Run GLM-5.1 with GGUF quantizations
Prebuilt GGUF weights published at unsloth/GLM-5.1-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/GLM-5.1-GGUFDeploy GLM-5.1 on Aquanode
Aquanode has no one-click deploy template for GLM-5.1; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1685 GB VRAM or more).
- 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.
- Run the command and connect to the resulting endpoint.
Launch a GPU podWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More GLM-5 models
- GLM-5 (753.9B, BF16)
- GLM-5-FP8 (753.9B, F8_E4M3)
- GLM-5.1-FP8 (753.9B, F8_E4M3)
- GLM-5.2-FP8 (753.3B, F8_E4M3)
- GLM-5.2 (753.3B, BF16)
Alternatives at this size
Other models for text-generation within about a third of GLM-5.1's 753.9B parameters, from other model lines.
- DeepSeek-R1 (684.5B, F8_E4M3)
- NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 (560.5B, BF16)
- Kimi-K2-Instruct (1026.4B, F8_E4M3)
- A.X-K2 (691.7B, F8_E4M3)
- MiMo-V2.5-Pro (1023.2B, F8_E4M3)
More on GLM-5.1
Best chat and assistants models: how GLM-5.1 ranks against the rest.
Related reading: H100 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.
