GL

GLM 4 32B Base 32K

GLMGGUF by bartowskiUpdated 2025-06-23
Download on Hugging Face
Parameters32.6B
Context32K
Layers61
Architectureglm4
Smallest quant9.0 GB
Quick answer

GLM 4 32B Base 32K needs about 20.7 GB of memory at Q4_K_M (a 19.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 9.0 GB (IQ2_XXS) to 65.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.

GLM‑4‑32B‑Base‑32K – 32B parameters, 32K context

GLM‑4‑32B‑Base‑32K is a 32.6B‑parameter model with a 32,000‑token context window. It extends the original GLM‑4‑32B‑Base to maintain performance across long sequences. The model is released under the MIT license.

Good at

  • Long‑context reasoning
  • Large‑scale text generation
  • Fine‑tuning for extended prompts

Limits

  • No vision support
  • Requires 8,192‑token context for memory estimates
  • License is MIT – no commercial restrictions

Best for

  • Document summarization over 32K tokens
  • Chatbot with extended memory
  • Research on long‑sequence tasks

Who it’s for. Developers needing a large‑parameter model that handles very long contexts. Researchers and hobbyists who can manage the memory footprint and want to fine‑tune on long‑sequence data.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS9.0 GB 10.0 GB
Too big Get file →
IQ2_XS9.9 GB 10.9 GB
Too big Get file →
IQ2_S10.4 GB 11.4 GB
Too big Get file →
IQ2_M11.3 GB 12.3 GB
Too big Get file →
Q2_K12.3 GB 13.3 GB
Too big Get file →
IQ3_XXS12.8 GB 13.8 GB
Too big Get file →
Q2_K_L13.2 GB 14.2 GB
Too big Get file →
IQ3_XS13.7 GB 14.7 GB
Too big Get file →
Q3_K_S14.4 GB 15.4 GB
Too big Get file →
IQ3_M14.8 GB 15.8 GB
Too big Get file →
Q3_K_M15.9 GB 16.9 GB
Too big Get file →
Q3_K_L17.2 GB 18.2 GB
Too big Get file →
IQ4_XS17.6 GB 18.6 GB
Too big Get file →
Q3_K_XL18.0 GB 19.0 GB
Too big Get file →
IQ4_NL18.6 GB 19.6 GB
Too big Get file →
Q4_018.6 GB 19.6 GB
Too big Get file →
Q4_K_S18.7 GB 19.7 GB
Too big Get file →
Q4_K_M19.7 GB 20.7 GB
Too big Get file →
Q4_K_L20.4 GB 21.4 GB
Too big Get file →
Q4_120.5 GB 21.6 GB
Too big Get file →
Q5_K_S22.5 GB 23.5 GB
Too big Get file →
Q5_K_M23.1 GB 24.1 GB
Too big Get file →
Q5_K_L23.7 GB 24.7 GB
Too big Get file →
Q6_K26.7 GB 27.7 GB
Too big Get file →
Q6_K_L27.2 GB 28.2 GB
Too big Get file →
Q8_034.6 GB 35.6 GB
Too big Get file →
BF1665.1 GB (2 parts) 66.2 GB
Too big Get file →

For 8–10 GB VRAM, use IQ2_XXS or IQ2_XS. For 12–15 GB VRAM, Q2_K or IQ3_XXS are suitable. For 20–25 GB VRAM, Q4_K_M or Q5_K_S provide a good balance of quality and memory usage. Estimates are approximate.

What GPU do you need for GLM 4 32B Base 32K?

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: the best quant that fits is IQ2_S (10.4 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (14.8 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_S (22.5 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (27.2 GB file, about 28.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.6 GB file, about 35.6 GB in use).

Which GLM 4 32B Base 32K quant should you choose?

Q4_K_M is the usual starting point for GLM 4 32B Base 32K: it balances file size and quality well. Here it is a 19.7 GB file.

The Q8_0 file is 34.6 GB, about 1.8 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 IQ2_XXS at 9.0 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

Architectureglm4
Parameters32.6B
Layers61
Trained context32,768 tokens
KV cache (fp16)61 KB per token

Source

Quantized bybartowski
FamilyGLM
Licensemit
Downloads (HF)2,312
Last updated2025-06-23

Frequently asked questions about GLM 4 32B Base 32K

How much VRAM does GLM 4 32B Base 32K need?

About 20.7 GB at Q4_K_M with an 8K context window. That is the 19.7 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 4 32B Base 32K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 4 32B Base 32K GGUF?

It depends on the quant: IQ2_XXS is 9.0 GB, IQ2_XS is 9.9 GB, IQ2_S is 10.4 GB, IQ2_M is 11.3 GB, Q2_K is 12.3 GB, IQ3_XXS is 12.8 GB and 21 more.

What context length does GLM 4 32B Base 32K support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.0 GB at 32K.

Where can I download GLM 4 32B Base 32K GGUF?

The files are on Hugging Face in the bartowski/arcee-ai_GLM-4-32B-Base-32K-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 4 32B Base 32K 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?

Use the IQ2_XXS or IQ2_XS quantization; they require about 10 GB of VRAM at 8,192‑token context.

Does this model support image inputs?

No, the model has no vision capabilities.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of GLM-4-32B-Base-32K

Similar models

Browse all →

More from bartowski

All by bartowski →

More GLM models

All GLM →

Other medium models

All medium models →