GL

GLM 5.3 0.6B A0.4B

GLMGGUF by mradermacherUpdated 2026-09-15
Download on Hugging Face
Parameters622M
Context1024K
Layers6
Architectureglm-dsa
Smallest quant0.3 GB
Quick answer

GLM 5.3 0.6B A0.4B needs about 1.0 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.3 GB (Q2_K) to 1.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

GLM 5.3 0.6B A0.4B – a small GLM MoE model

GLM 5.3 0.6B A0.4B is a 0.62B parameter model with 0.4B activated parameters. It uses the glm-dsa architecture and supports reasoning and tools. The model is released under the MIT license.

Good at

  • Reasoning
  • Tool usage
  • Small‑parameter inference

Limits

  • No vision support
  • Large context requires high VRAM
  • No FP8 quant available

Best for

  • Embedded inference
  • Rapid prototyping
  • Low‑cost deployment

Who it’s for. Developers needing a lightweight GLM model for local inference. The model is suitable for testing, development, and small‑scale deployments where memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.3 GB 0.9 GB
Fits Get file →
Q3_K_S0.3 GB 0.9 GB
Fits Get file →
Q3_K_M0.4 GB 1.0 GB
Fits Get file →
Q3_K_L0.4 GB 1.0 GB
Fits Get file →
IQ4_XS0.4 GB 1.0 GB
Fits Get file →
Q4_K_S0.4 GB 1.0 GB
Fits Get file →
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
Q5_K_S0.5 GB 1.1 GB
Fits Get file →
Q5_K_M0.5 GB 1.1 GB
Fits Get file →
Q6_K0.5 GB 1.1 GB
Fits Get file →
Q8_00.7 GB 1.3 GB
Fits Get file →
F161.3 GB 1.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M or Q4_K_S (≈1 GB file, 1 GB VRAM). For 4 GB VRAM, Q3_K_M or Q3_K_S (≈0.35–0.34 GB file, 0.9 GB VRAM). Larger VRAM allows Q5_K_S or Q5_K_M (≈0.46 GB file, 1.1 GB VRAM). Estimates are approximate.

What GPU do you need for GLM 5.3 0.6B A0.4B?

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: the best quant that fits is F16 (1.3 GB file, about 1.9 GB in use).

Which GLM 5.3 0.6B A0.4B quant should you choose?

Q4_K_M is the usual starting point for GLM 5.3 0.6B A0.4B: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.7 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.3 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

Architectureglm-dsa
Parameters622M (approximate, mixture of experts)
Active parameters0.4B
Layers6
Trained context1,048,576 tokens
KV cache (fp16)13 KB per token

Source

Quantized bymradermacher
FamilyGLM
Licensemit
Downloads (HF)908
Last updated2026-09-15

Frequently asked questions about GLM 5.3 0.6B A0.4B

How much VRAM does GLM 5.3 0.6B A0.4B need?

About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.4 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 0.6B A0.4B on an 8 GB GPU?

Yes, with F16: the 1.3 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GLM 5.3 0.6B A0.4B GGUF?

It depends on the quant: Q2_K is 0.3 GB, Q3_K_S is 0.3 GB, Q3_K_M is 0.4 GB, Q3_K_L is 0.4 GB, IQ4_XS is 0.4 GB, Q4_K_S is 0.4 GB and 6 more.

What context length does GLM 5.3 0.6B A0.4B 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 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download GLM 5.3 0.6B A0.4B GGUF?

The files are on Hugging Face in the mradermacher/GLM-5.3-0.6B-A0.4B-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 0.6B A0.4B 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 this model on 8 GB VRAM?

Yes, use Q4_K_M or Q4_K_S which require about 1 GB VRAM at 8 k context.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More GLM models

All GLM →

Other tiny models

All tiny models →