GL

GLM 5.3 Flash

GLMGGUF by unslothUpdated 2026-10-05
Download on Hugging Face
Parameters320B
Context1024K
Layers46
Architectureglm5-next
Smallest quant93.1 GB
Quick answer

GLM 5.3 Flash needs about 197.4 GB of memory at Q3_K_XL (a 147.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 12 quants, from 93.1 GB (IQ1_S) to 641.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 197.6 GB.

GLM 5.3 Flash – 320B multimodal model with 18B active parameters

GLM 5.3 Flash is a multimodal model in the GLM family. It contains 320B total parameters and 18B active parameters, trained on 1,048,576 context tokens. The model supports vision and is released under the MIT license.

Good at

  • Vision and text tasks
  • Large context handling
  • Efficient active parameter usage

Limits

  • Requires large VRAM for higher quants
  • No explicit language support list
  • Limited to 1,048,576 token context

Best for

  • Multimodal content generation
  • Long‑form document analysis
  • Vision‑enabled chat applications

Who it’s for. Developers and researchers needing a multimodal model with a large context window. The model is suitable for applications that can allocate sufficient GPU memory for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S93.1 GB (3 parts) 143.0 GB
Too big Get file →
IQ1_M97.6 GB (3 parts) 147.5 GB
Too big Get file →
IQ2_XXS101.8 GB (4 parts) 151.7 GB
Too big Get file →
Q2_K_XL108.7 GB (4 parts) 158.6 GB
Too big Get file →
IQ3_XXS120.4 GB (4 parts) 170.3 GB
Too big Get file →
Q3_K_XL147.5 GB (4 parts) 197.4 GB
Too big Get file →
IQ4_XS156.8 GB (5 parts) 206.7 GB
Too big Get file →
Q4_K_XL199.7 GB (6 parts) 249.6 GB
Too big Get file →
Q5_K_XL240.3 GB (6 parts) 290.2 GB
Too big Get file →
Q6_K_XL291.8 GB (7 parts) 341.7 GB
Too big Get file →
Q8_0341.0 GB (8 parts) 390.9 GB
Too big Get file →
BF16641.6 GB (14 parts) 691.5 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S or IQ1_M quants (file sizes 93–98 GB, memory ~144–148 GB at 8 k context). For 16‑GB VRAM, Q2_K_XL or IQ2_XXS are suitable (est. 158–152 GB). Larger VRAM allows Q4_K_XL or Q5_K_XL for higher quality.

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.

Which GLM 5.3 Flash quant should you choose?

Q3_K_XL (147.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 93.1 GB, with the quality trade-offs that come with fewer bits. 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

Architectureglm5-next
Parameters320B (approximate, mixture of experts)
Layers46
Trained context1,048,576 tokens
KV cache (fp16)5888 KB per token

Source

Quantized byunsloth
FamilyGLM
Licensemit
Downloads (HF)837,516
Last updated2026-10-05

Frequently asked questions about GLM 5.3 Flash

How much VRAM does GLM 5.3 Flash need?

About 197.4 GB at Q3_K_XL with an 8K context window. That is the 147.5 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 143.0 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: IQ1_S is 93.1 GB, IQ1_M is 97.6 GB, IQ2_XXS is 101.8 GB, Q2_K_XL is 108.7 GB, IQ3_XXS is 120.4 GB, Q3_K_XL is 147.5 GB and 6 more.

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 49.4 GB at 8K and 197.6 GB at 32K.

Where can I download GLM 5.3 Flash GGUF?

The files are on Hugging Face in the unsloth/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?

Only the lowest quants IQ1_S or IQ1_M can be attempted, but memory usage is still high; 8 GB VRAM is generally insufficient.

Does the model support vision?

Yes, GLM 5.3 Flash has detected vision capability.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of GLM-5.3-Flash

Similar models

Browse all →

More from unsloth

All by unsloth →

More GLM models

All GLM →

Other large models

All large models →