GLM 5.3 Flash needs about 98.3 GB of memory at IQ2_XXS (a 87.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 87.3 GB (IQ2_XXS) to 112.4 GB (IQ3_XXS).
GLM 5.3 Flash – 320 B total, 17 B active parameters, multimodal LLM
GLM 5.3 Flash is a 320.6 B parameter model with 17.3 B active parameters. It uses a hybrid sparse‑linear attention architecture and supports long‑context serving. The model is available in two hand‑mixed GGUF quantizations.
Good at
- Long‑context inference up to 1 M tokens
- Hybrid sparse‑linear attention for low VRAM usage
- Multimodal capabilities via GLM‑5 series
Limits
- Requires 87 GB or 112 GB GGUF file
- Large VRAM needed for 8 k context (≈98 GB or 126 GB)
- No vision support in the provided quantizations
Best for
- Serving long‑context chat applications
- Research on sparse‑attention models
- Deploying multimodal LLMs on high‑end GPUs
Who it’s for. Developers and researchers needing a large multimodal LLM with efficient long‑context handling. The model is suited for environments with high VRAM capacity and a need for hybrid attention performance.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 87.3 GB (2 parts) | 98.3 GB | Too big | Get file → | |
| IQ3_XXS | 112.4 GB (3 parts) | 126.4 GB | Too big | Get file → |
For 8 k context, the IQ2_XXS quant (~87 GB) uses about 98 GB VRAM, while IQ3_XXS (~112 GB) uses about 126 GB. Choose IQ2_XXS for tighter memory budgets and IQ3_XXS for higher precision when VRAM allows.
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 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 Flash quant should you choose?
IQ2_XXS (87.3 GB) is the middle option in this repository. 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
Source
Frequently asked questions about GLM 5.3 Flash
How much VRAM does GLM 5.3 Flash need?
About 98.3 GB at IQ2_XXS with an 8K context window. That is the 87.3 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 98.3 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: IQ2_XXS is 87.3 GB, IQ3_XXS is 112.4 GB.
What context length does GLM 5.3 Flash support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download GLM 5.3 Flash GGUF?
The files are on Hugging Face in the aj9o9/GLM-5.3-Flash-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 smallest GGUF quant requires about 98 GB VRAM at 8 k context, so 8 GB is insufficient.
What framework can I use to serve this model locally?
Supported frameworks include SGLang, vLLM, TokenSpeed, Transformers, KTransformers, and Unsloth.
Does the model support vision?
The provided GGUF files do not include vision support; the model is text‑only in these builds.