GL

GLM 5.3 Flash Maya M Derisked IQ2 S

GLMGGUF by peasantsmithUpdated 2026-10-10
Download on Hugging Face
Parameters321B
Context1024K
Layers46
Architectureglm5-next
Smallest quant116.0 GB
Quick answer

GLM 5.3 Flash Maya M Derisked IQ2 S needs about 165.9 GB of memory at IQ2_S (a 116.0 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 197.6 GB.

GLM 5.3 Flash Maya M Derisked IQ2 S – 321 B parameter LLM with DWM for reduced refusal

GLM‑5.3‑Flash Maya‑M Derisked IQ2_S is a 321 B parameter mixture‑of‑experts model. It uses a 1 048 576‑token context and is released under the MIT license. The model retains the original IQ2_S mixed‑storage quantization and includes the NextN draft layer.

Good at

  • Large context handling
  • Mixture‑of‑experts inference
  • Chat‑style reasoning

Limits

  • No vision support
  • Requires 165.9 GB VRAM at 8 k context
  • MIT license only

Best for

  • Long‑form content generation
  • Complex reasoning tasks
  • Tool‑call workflows

Who it’s for. Developers and researchers needing a large‑context LLM with a mixture‑of‑experts architecture. The model is suitable for systems with substantial GPU memory and a need for reduced refusal behavior.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_S116.0 GB (3 parts) 165.9 GB
Too big Get file →

For 8 k context the IQ2_S quant requires about 165.9 GB VRAM. If you have a 30 GB GPU, split the model across two GPUs or use a larger memory pool. The file is split into three shards, each 116 GB.

What GPU do you need for GLM 5.3 Flash Maya M Derisked IQ2 S?

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 Maya M Derisked IQ2 S quant should you choose?

IQ2_S (116.0 GB) is the middle option in this repository. 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
Parameters321B (approximate, mixture of experts)
Layers46
Trained context1,048,576 tokens
KV cache (fp16)5888 KB per token

Source

Quantized bypeasantsmith
FamilyGLM
Licensemit
Downloads (HF)26,040
Last updated2026-10-10

Frequently asked questions about GLM 5.3 Flash Maya M Derisked IQ2 S

How much VRAM does GLM 5.3 Flash Maya M Derisked IQ2 S need?

About 165.9 GB at IQ2_S with an 8K context window. That is the 116.0 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 Maya M Derisked IQ2 S on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 165.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 5.3 Flash Maya M Derisked IQ2 S GGUF?

It depends on the quant: IQ2_S is 116.0 GB.

What context length does GLM 5.3 Flash Maya M Derisked IQ2 S 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 Maya M Derisked IQ2 S GGUF?

The files are on Hugging Face in the peasantsmith/GLM-5.3-Flash-Maya-M-Derisked-IQ2_S-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 Maya M Derisked IQ2 S 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 a single 30 GB GPU?

No, the model needs approximately 165.9 GB VRAM at 8 k context, so a single 30 GB GPU is insufficient.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license does it use?

The model is released under the MIT license.

Other GGUFs of GLM-5.3-Flash-Maya-GGUF

Similar models

Browse all →

More from peasantsmith

All by peasantsmith →

More GLM models

All GLM →

Other large models

All large models →