GL

GLM 5.3 Flash GGUF DGX Spark

GLMGGUF by taurusduanUpdated 2026-09-29
Download on Hugging Face
Parameters279B
Context1024K
Layers45
Architectureglm5-next
Smallest quant84.9 GB
Quick answer

GLM 5.3 Flash GGUF DGX Spark needs about 91.5 GB of memory at its main file (a 84.9 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 24.2 GB.

GLM 5.3 Flash GGUF DGX Spark is a 279B-parameter GLM model in GGUF format, quantized by taurusduan. Its trained context length is 1024K tokens. The repository has 1 quant file, from 84.9 GB to 84.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—84.9 GB (2 parts) 91.5 GB
Too big Get file →

What GPU do you need for GLM 5.3 Flash GGUF DGX Spark?

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

Architectureglm5-next
Parameters279B (approximate, mixture of experts)
Layers45
Trained context1,048,576 tokens
KV cache (fp16)720 KB per token

Source

Quantized bytaurusduan
FamilyGLM
Licensemit
Downloads (HF)280
Last updated2026-09-29

Frequently asked questions about GLM 5.3 Flash GGUF DGX Spark

How much VRAM does GLM 5.3 Flash GGUF DGX Spark need?

About 91.5 GB at its main file with an 8K context window. That is the 84.9 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 GGUF DGX Spark on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 91.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 5.3 Flash GGUF DGX Spark GGUF?

It depends on the quant: file is 84.9 GB.

What context length does GLM 5.3 Flash GGUF DGX Spark 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 6.0 GB at 8K and 24.2 GB at 32K.

Where can I download GLM 5.3 Flash GGUF DGX Spark GGUF?

The files are on Hugging Face in the taurusduan/GLM-5.3-Flash-GGUF-DGX-Spark 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 GGUF DGX Spark 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.

Other GGUFs of GLM-5.3-Flash

Similar models

Browse all →

More from taurusduan

All by taurusduan →

More GLM models

All GLM →

Other large models

All large models →