GL

GLM 5.3

GLMGGUF by unslothUpdated 2026-08-29
Download on Hugging Face
Parameters754B
Context1024K
Layers79
Architectureglm-dsa
Smallest quant216.7 GB
Quick answer

GLM 5.3 needs about 344.9 GB of memory at Q3_K_XL (a 343.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 12 quants, from 216.7 GB (IQ1_S) to 1508.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

GLM‑5.3 – 750 Billion‑parameter open‑weights model for coding and cyber tasks

GLM‑5.3 builds on GLM‑5.2 with post‑training improvements. It excels at complex coding and long‑horizon tasks, and shows strong performance on cyber vulnerability discovery. The model supports a maximum context of 1,048,576 tokens.

Good at

  • Advanced coding tasks
  • Long‑horizon reasoning
  • Cyber vulnerability analysis

Limits

  • Requires large VRAM for full precision
  • No vision support
  • License type is other

Best for

  • Developers needing high‑quality code generation
  • Security analysts testing exploit chains
  • Researchers exploring long‑context language models

Who it’s for. Engineers and researchers who need an open‑weights model capable of deep coding and cyber analysis. The model is suitable for environments that can accommodate its memory demands and support the required frameworks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S216.7 GB (6 parts) 218.6 GB
Too big Get file →
IQ1_M228.5 GB (6 parts) 230.4 GB
Too big Get file →
IQ2_M238.6 GB (6 parts) 240.5 GB
Too big Get file →
Q2_K_XL253.9 GB (7 parts) 255.8 GB
Too big Get file →
IQ3_XXS281.7 GB (7 parts) 283.6 GB
Too big Get file →
Q3_K_XL343.0 GB (9 parts) 344.9 GB
Too big Get file →
IQ4_XS365.3 GB (9 parts) 367.2 GB
Too big Get file →
Q4_K_XL467.3 GB (11 parts) 469.2 GB
Too big Get file →
Q5_K_XL562.5 GB (13 parts) 564.4 GB
Too big Get file →
Q6_K_XL684.4 GB (16 parts) 686.3 GB
Too big Get file →
Q8_0801.4 GB (17 parts) 803.3 GB
Too big Get file →
BF161508.0 GB (33 parts) 1509.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (≈218–230 GB memory at 8k context). For 16 GB VRAM, IQ2_M or Q2_K_XL (≈240–256 GB). For 32 GB VRAM, Q3_K_XL or Q4_K_XL (≈345–470 GB). Memory estimates are approximate.

What GPU do you need for GLM 5.3?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which GLM 5.3 quant should you choose?

Q3_K_XL (343.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 216.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm-dsa
Parameters754B (approximate, mixture of experts)
Layers79
Trained context1,048,576 tokens
KV cache (fp16)168 KB per token

Source

Quantized byunsloth
FamilyGLM
Base modelzai-org/GLM-5.3
Licenseother
Downloads (HF)359,063
Last updated2026-08-29

Frequently asked questions about GLM 5.3

How much VRAM does GLM 5.3 need?

About 344.9 GB at Q3_K_XL with an 8K context window. That is the 343.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run GLM 5.3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 218.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 5.3 GGUF?

It depends on the quant: IQ1_S is 216.7 GB, IQ1_M is 228.5 GB, IQ2_M is 238.6 GB, Q2_K_XL is 253.9 GB, IQ3_XXS is 281.7 GB, Q3_K_XL is 343.0 GB and 6 more.

What context length does GLM 5.3 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download GLM 5.3 GGUF?

The files are on Hugging Face in the unsloth/GLM-5.3-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does GLM 5.3 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run GLM‑5.3 on 8 GB VRAM?

Use the IQ1_S or IQ1_M quantized files; they require roughly 218–230 GB memory at 8k context, which is beyond 8 GB VRAM, so it is not feasible.

Does GLM‑5.3 support vision tasks?

No, the model has no vision capabilities.

What frameworks can run GLM‑5.3 locally?

Supported frameworks include SGLang, vLLM, TokenSpeed, Transformers, KTransformers, Unsloth, and Ascend NPU platforms.

Other GGUFs of GLM-5.3

Similar models

Browse all →

More from unsloth

All by unsloth →

More GLM models

All GLM →

Other large models

All large models →