GL

GLM 5.2 MaxMin108

GLMGGUF by turintechUpdated 2026-10-26
Download on Hugging Face
Parameters325B
Context1024K
Layers78
Architectureglm-dsa
Smallest quant102.8 GB
Quick answer

GLM 5.2 MaxMin108 needs about 104.7 GB of memory at IQ2_M (a 102.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 102.8 GB (IQ2_M) to 107.7 GB (IQ2_M). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

GLM 5.2 MaxMin108 – 325 B parameter LLM with 1 M‑token context

GLM 5.2 MaxMin108 is a 325 billion‑parameter model built on the GLM‑DSA architecture. It supports a solid 1 M‑token context and is optimized for long‑horizon reasoning and coding tasks. The model is released under an MIT license and is available as a 2‑bit IQ2_M GGUF.

Good at

  • Long‑horizon reasoning
  • Advanced coding with flexible effort
  • Large context handling

Limits

  • Requires large memory – 104–110 GB at 8 k context
  • Six shards needed for full model
  • No vision support

Best for

  • Chatting with 1 M‑token context
  • Complex code generation
  • Research on long‑sequence tasks

Who it’s for. Developers and researchers who need a high‑capacity LLM for tasks that exceed typical 8 k or 32 k token limits. The model is suitable for environments with 128 GB RAM or larger and for users who prefer an open‑source, MIT‑licensed solution.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M102.8 GB (6 parts) 104.7 GB
Too big Get file →
IQ2_M107.7 GB (6 parts) 109.6 GB
Too big Get file →

For a 128 GB machine, the 102.84 GB IQ2_M shard set is recommended; it uses about 104.7 GB at 8 k context. If more memory is available, the 107.73 GB set uses about 109.6 GB. Both sets require six shards and are approximate estimates.

What GPU do you need for GLM 5.2 MaxMin108?

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 5.2 MaxMin108 quant should you choose?

IQ2_M (102.8 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
Parameters325B (approximate, mixture of experts)
Layers78
Trained context1,048,576 tokens
KV cache (fp16)166 KB per token

Source

Quantized byturintech
FamilyGLM
Base modelzai-org/GLM-5.2
Licensemit
Downloads (HF)882
Last updated2026-10-26

Frequently asked questions about GLM 5.2 MaxMin108

How much VRAM does GLM 5.2 MaxMin108 need?

About 104.7 GB at IQ2_M with an 8K context window. That is the 102.8 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 5.2 MaxMin108 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 104.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 5.2 MaxMin108 GGUF?

It depends on the quant: IQ2_M is 102.8 GB, IQ2_M is 107.7 GB.

What context length does GLM 5.2 MaxMin108 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 5.2 MaxMin108 GGUF?

The files are on Hugging Face in the turintech/GLM-5.2-MaxMin108-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 5.2 MaxMin108 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 5.2 MaxMin108 on 8 GB VRAM?

No. The model requires over 100 GB of RAM at 8 k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

How many shards are needed to run the model?

Six shards are required for the full model.

Other GGUFs of GLM-5.2

Similar models

Browse all →

More from turintech

All by turintech →

More GLM models

All GLM →

Other large models

All large models →