GL

GLM 5.3 Flash Maya

GLMGGUF by peasantsmithUpdated 2026-10-09
Download on Hugging Face
Parameters370B
Context64K
Layers1
Architecturellama
Smallest quant0.0 GB
Quick answer

GLM 5.3 Flash Maya needs about 97.1 GB of memory at IQ2_XXS (a 96.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 0.0 GB to 156.3 GB (IQ3_S). Longer context needs more: at 32K tokens the KV cache alone adds about 0.5 GB.

GLM‑5.3‑Flash Maya – a multimodal GGUF model with 370 B parameters

GLM‑5.3‑Flash Maya is a multimodal GGUF model based on the GLM‑5.3‑Flash architecture. It contains 370 B parameters and supports vision tasks. The model is released under the MIT license and can be run with llama.cpp or other GGUF‑compatible frameworks.

Good at

  • Vision‑enabled multimodal responses
  • Large context handling up to 65 536 tokens
  • Efficient deployment on GPUs with 24 GB VRAM

Limits

  • Requires 370 B parameters – large memory footprint
  • No explicit language support listed
  • Vision only – no text‑only specialized modes

Best for

  • Developers needing multimodal inference on local hardware
  • Researchers testing vision‑language models
  • Edge deployments with limited GPU memory

Who it’s for. This model is suitable for developers and researchers who need a multimodal LLM that can run locally. It is ideal for those who want to experiment with vision tasks without relying on cloud services.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.6 GB
Fits Get file →
IQ2_XXS94.7 GB (3 parts) 95.3 GB
Too big Get file →
IQ2_XXS96.5 GB (3 parts) 97.1 GB
Too big Get file →
IQ2_S116.0 GB (3 parts) 116.6 GB
Too big Get file →
IQ3_S156.3 GB (4 parts) 157.0 GB
Too big Get file →

For 8 GB VRAM, use the IQ2_XXS quantization (94.7 GB file) and split into 3 shards; memory estimate is ~95 GB at 8 k context. For 24 GB VRAM, the IQ2_XXS quantization (94.7 GB) is also suitable, providing about 1.5 GB more room for experts. For larger GPUs, the IQ3_S quantization (156 GB) can be used, but requires more memory.

What GPU do you need for GLM 5.3 Flash Maya?

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 the main file (0.0 GB file, about 0.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.6 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.6 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.6 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.6 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.6 GB in use).

Which GLM 5.3 Flash Maya quant should you choose?

IQ2_XXS (96.5 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.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters370B
Layers1
Trained context65,536 tokens
KV cache (fp16)16 KB per token

Source

Quantized bypeasantsmith
FamilyGLM
Licensemit
Downloads (HF)534,728
Last updated2026-10-09

Frequently asked questions about GLM 5.3 Flash Maya

How much VRAM does GLM 5.3 Flash Maya need?

About 97.1 GB at IQ2_XXS with an 8K context window. That is the 96.5 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 Maya on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GLM 5.3 Flash Maya GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 94.7 GB, IQ2_XXS is 96.5 GB, IQ2_S is 116.0 GB, IQ3_S is 156.3 GB.

What context length does GLM 5.3 Flash Maya support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.5 GB at 32K.

Where can I download GLM 5.3 Flash Maya GGUF?

The files are on Hugging Face in the peasantsmith/GLM-5.3-Flash-Maya-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 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 Maya on 8 GB VRAM?

No, the smallest quantized file is 94.7 GB, which exceeds 8 GB VRAM. You would need a larger GPU or off‑device memory.

Does GLM‑5.3‑Flash Maya support text‑only tasks?

The model is multimodal with vision support; text‑only tasks are supported but the model is optimized for vision.

Other GGUFs of GLM-5.3-Flash

Similar models

Browse all →

More from peasantsmith

All by peasantsmith →

More GLM models

All GLM →

Other large models

All large models →