GL

GLM 5.3 ewaste edition

GLMGGUF by SixVoltsUpdated 2026-10-03
Download on Hugging Face
Parameters753B
Context1024K
Layers79
Architectureglm-dsa
Smallest quant7.2 GB
Quick answer

GLM 5.3 ewaste edition needs about 321.3 GB of memory at Q3_K_M (a 319.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 7.2 GB (Q3_K_M) to 433.6 GB (Q4_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

GLM‑5.3 e‑waste edition – a lightweight GGUF quantization of the 753‑billion‑parameter GLM‑5.3

GLM‑5.3 e‑waste edition is a quantized version of the 753‑billion‑parameter GLM‑5.3 model. It supports reasoning and tools, and is optimized for older CPUs and GPUs. The model retains the GLM‑5.3 architecture and post‑training improvements.

Good at

  • Reasoning
  • Tool usage
  • Long‑context handling

Limits

  • No vision support
  • Requires large VRAM for full quant
  • MIT license only

Best for

  • Chatbots with reasoning
  • Code generation
  • Tool‑enabled workflows

Who it’s for. Developers building lightweight LLM applications on older hardware. The model is ideal for users who need a large‑parameter model but cannot afford high‑end GPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M7.2 GB 9.2 GB
Too big Get file →
Q2_K_XL245.6 GB (6 parts) 247.5 GB
Too big Get file →
Q3_K_M319.4 GB (8 parts) 321.3 GB
Too big Get file →
Q3_K_XL337.3 GB (8 parts) 339.2 GB
Too big Get file →
Q4_K_XL433.6 GB (10 parts) 435.5 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_M (file size 7.25 GB, estimated 9.2 GB memory at 8 k context). For 16 GB VRAM, Q4_K_XL (file size 433.56 GB, estimated 435.5 GB memory) is the next option. Sharded variants can reduce peak memory but increase load time.

What GPU do you need for GLM 5.3 ewaste edition?

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: the best quant that fits is Q3_K_M (7.2 GB file, about 9.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (7.2 GB file, about 9.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q3_K_M (7.2 GB file, about 9.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_M (7.2 GB file, about 9.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q3_K_M (7.2 GB file, about 9.2 GB in use).

Which GLM 5.3 ewaste edition quant should you choose?

Q3_K_M (319.4 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 Q3_K_M at 7.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm-dsa
Parameters753B (approximate, mixture of experts)
Layers79
Trained context1,048,576 tokens
KV cache (fp16)168 KB per token

Source

Quantized bySixVolts
FamilyGLM
Base modelzai-org/GLM-5.3
Licensemit
Downloads (HF)746
Last updated2026-10-03

Frequently asked questions about GLM 5.3 ewaste edition

How much VRAM does GLM 5.3 ewaste edition need?

About 321.3 GB at Q3_K_M with an 8K context window. That is the 319.4 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 ewaste edition on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 5.3 ewaste edition GGUF?

It depends on the quant: Q3_K_M is 7.2 GB, Q2_K_XL is 245.6 GB, Q3_K_M is 319.4 GB, Q3_K_XL is 337.3 GB, Q4_K_XL is 433.6 GB.

What context length does GLM 5.3 ewaste edition 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 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download GLM 5.3 ewaste edition GGUF?

The files are on Hugging Face in the SixVolts/GLM-5.3-ewaste-edition-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 ewaste edition 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 e‑waste edition on 8 GB VRAM?

The Q3_K_M quant requires about 9.2 GB memory at 8 k context, so it will not fit in 8 GB VRAM.

Does this model support vision?

No, the model has no vision capabilities.

What license does it use?

The model is released under the MIT license.

Other GGUFs of GLM-5.3

Similar models

Browse all →

More from SixVolts

All by SixVolts →

More GLM models

All GLM →

Other large models

All large models →