GLM-5.3-Flash needs about 166.3 GB of memory at its main file (a 117.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 117.5 GB to 137.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 193.3 GB.
GLM-5.3-Flash, a 320B‑parameter multimodal model in GGUF format
GLM-5.3-Flash is a 320B‑parameter multimodal model with 18B active parameters. It supports vision and long‑context up to 1,048,576 tokens. The GGUF files are quantized with GSQ‑RCO and include a vision projector.
Good at
- Vision tasks
- Long‑context reasoning
- Multimodal generation
Limits
- No text‑only inference without vision projector
- Requires large VRAM for full model
- License is MIT
Best for
- Vision‑enabled chatbots
- Long‑form content analysis
- Multimodal research prototypes
Who it’s for. Developers and researchers needing a large multimodal model that can be run locally with GGUF. The model is suitable for applications that require both vision and extensive context handling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 117.5 GB | 166.3 GB | Too big | Get file → | |
| — | 137.1 GB | 185.9 GB | Too big | Get file → |
For 8 GB VRAM, use the 117.48 GB GGUF file; it estimates 166.3 GB memory at 8 k context. For 16 GB VRAM, use the 137.07 GB file; it estimates 185.9 GB memory at 8 k context. Memory estimates are approximate.
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 166.3 GB at its main file with an 8K context window. That is the 117.5 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 166.3 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: file is 117.5 GB, file is 137.1 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 taurusduan/GLM-5.3-Flash-GSQ-RCO-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?
The 117.48 GB GGUF file estimates 166.3 GB memory at 8 k context, which exceeds 8 GB VRAM. It is not feasible without significant off‑loading.
Does the model support vision?
Yes, the GGUF files include a BF16 vision projector for multimodal use.
What license applies to the GGUF files?
The files are released under the MIT license.