GM

gml 5.2 iq1 s

GmlGGUF by rit11Updated 2026-07-23
Download on Hugging Face
Parameters96B
Context1024K
Layers79
Architectureglm-dsa
Smallest quant19.2 GB
Quick answer

gml 5.2 iq1 s needs about 21.1 GB of memory at IQ1_S (a 19.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

gml 5.2 iq1 s is a 96B-parameter Gml model in GGUF format, quantized by rit11. Its trained context length is 1024K tokens. The repository has 1 quant file, from 19.2 GB (IQ1_S) to 19.2 GB (IQ1_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S19.2 GB (2 parts) 21.1 GB
Too big Get file →

What GPU do you need for gml 5.2 iq1 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: the best quant that fits is IQ1_S (19.2 GB file, about 21.1 GB in use).

Which gml 5.2 iq1 s quant should you choose?

IQ1_S (19.2 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

Architectureglm-dsa
Parameters96B (approximate, mixture of experts)
Layers79
Trained context1,048,576 tokens
KV cache (fp16)168 KB per token

Source

Quantized byrit11
FamilyGml
Licensemit
Downloads (HF)43
Last updated2026-07-23

Frequently asked questions about gml 5.2 iq1 s

How much VRAM does gml 5.2 iq1 s need?

About 21.1 GB at IQ1_S with an 8K context window. That is the 19.2 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 gml 5.2 iq1 s on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gml 5.2 iq1 s GGUF?

It depends on the quant: IQ1_S is 19.2 GB.

What context length does gml 5.2 iq1 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 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download gml 5.2 iq1 s GGUF?

The files are on Hugging Face in the rit11/gml-5.2-iq1-s repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gml 5.2 iq1 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.

Similar models

Browse all →

Other large models

All large models →