GLM 5.3 needs about 471.1 GB of memory at Q4_K_M (a 469.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 1.1 GB to 561.7 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
GLM 5.3 – a large MoE model with strong reasoning and tool use
GLM 5.3 is a 753‑billion‑parameter model that supports reasoning and tool usage. It is trained on a 1,048,576‑token context and is available in several quantized GGUF formats. The model is part of the GLM family and uses the glm‑dsa architecture.
Good at
- Reasoning
- Tool integration
- Long‑context handling
Limits
- Large memory requirement for full precision
- No vision support
- License type is other
Best for
- Complex coding tasks
- Cybersecurity analysis
- Long‑horizon planning
Who it’s for. Developers and researchers who need a large, multi‑expert model for reasoning and tool‑based workflows. The model is suitable for applications that can accommodate its high memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.1 GB | 3.0 GB | Fits | Get file → | |
| IQ2_S | 259.1 GB (7 parts) | 261.0 GB | Too big | Get file → | |
| IQ3_S | 285.6 GB (7 parts) | 287.5 GB | Too big | Get file → | |
| IQ4_XS | 367.2 GB (9 parts) | 369.2 GB | Too big | Get file → | |
| Q4_K_M | 469.2 GB (11 parts) | 471.1 GB | Too big | Get file → | |
| Q5_K_M | 561.7 GB (13 parts) | 563.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_S (259.13 GB file, 261 GB memory at 8 k context). For 16 GB VRAM, IQ3_S (285.55 GB file, 287.5 GB memory). For 32 GB VRAM, Q4_K_M (469.17 GB file, 471.1 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: the best quant that fits is the main file (1.1 GB file, about 3.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 3.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 3.0 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 3.0 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 3.0 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 3.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 3.0 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 3.0 GB in use).
Which GLM 5.3 quant should you choose?
Q4_K_M is the usual starting point for GLM 5.3: it balances file size and quality well. Here it is a 469.2 GB file.
If memory is tight, the smallest file is the first one in the table at 1.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM 5.3
How much VRAM does GLM 5.3 need?
About 471.1 GB at Q4_K_M with an 8K context window. That is the 469.2 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?
Yes, with the smaller files: the 1.1 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM 5.3 GGUF?
It depends on the quant: file is 1.1 GB, IQ2_S is 259.1 GB, IQ3_S is 285.6 GB, IQ4_XS is 367.2 GB, Q4_K_M is 469.2 GB, Q5_K_M is 561.7 GB.
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 AesSedai/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 IQ2_S quantization; it requires about 261 GB memory at 8 k context, so it will not fit on 8 GB VRAM.
Does GLM 5.3 support vision tasks?
No, the model does not have vision capabilities.
What is the context length of GLM 5.3?
It was trained on 1,048,576 tokens and supports that context length.