GLM-5.3-Flash needs about 162.4 GB of memory at its main file (a 113.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 193.3 GB.
GLM-5.3-Flash 313B MoE model in GGUF format
GLM-5.3-Flash is a 313‑billion‑parameter MoE model with a trained context of 1,048,576 tokens. The GGUF file is 113.59 GB and requires about 162.4 GB of VRAM at an 8 k context. It is released under the MIT license.
Good at
- Large context handling
- High‑parameter MoE architecture
- Extensive token capacity
Limits
- Requires >162 GB VRAM
- No vision support in this file
- Needs a llama.cpp fork with MoE cache
Best for
- Long‑form document analysis
- Complex reasoning tasks
- High‑capacity inference on powerful GPUs
Who it’s for. Developers and researchers who need a massive context window and MoE capabilities on a single GPU setup. The model is suitable for advanced inference workloads that can accommodate its memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 113.6 GB | 162.4 GB | Too big | Get file → |
The only available quantization is the 113.59 GB file. It is suitable for systems with at least 162.4 GB VRAM at 8 k context. No other quants are provided, so this is the recommended choice for large‑memory budgets.
What GPU do you need for GLM-5.3-Flash?
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.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM-5.3-Flash
How much VRAM does GLM-5.3-Flash need?
About 162.4 GB at its main file with an 8K context window. That is the 113.6 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-Flash on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 162.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM-5.3-Flash GGUF?
It depends on the quant: file is 113.6 GB.
What context length does GLM-5.3-Flash 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 48.3 GB at 8K and 193.3 GB at 32K.
Where can I download GLM-5.3-Flash GGUF?
The files are on Hugging Face in the neuralll/GLM-5.3-Flash-GSQ-RCO-3.0bit-Q4Kattn-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-Flash use?
Hugging Face lists the license as mit. 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-Flash on 8 GB VRAM?
No. The model requires about 162.4 GB VRAM at an 8 k context, far beyond 8 GB.
Does this GGUF file support vision tasks?
No. The vision projector is a separate BF16 file; this GGUF contains only the language model.
Is a chat template available?
No. The model is evaluated without a chat template and does not include one.