GL

THUDM/GLM-4-32B-Base-0414

GLMGGUF by DevQuasar-12Updated 2025-04-16
Download on Hugging Face
Parameters32.6B
Context32K
Layers61
Architectureglm4
Smallest quant12.3 GB
Quick answer

THUDM/GLM-4-32B-Base-0414 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 11 quants, from 12.3 GB (Q2_K) to 65.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.

GLM‑4‑32B‑Base‑0414 – 32 billion‑parameter LLM in GGUF format

GLM‑4‑32B‑Base‑0414 is a 32 billion‑parameter language model based on the glm4 architecture. It was pre‑trained on 15 T of high‑quality data and fine‑tuned with human preference alignment for instruction following, code generation, and function calling. The model supports a 32 768‑token context window and is released under the MIT license.

Good at

  • Instruction following
  • Engineering code generation
  • Function calling

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • Requires 8 k context for memory estimates

Best for

  • Local deployment of large‑scale LLMs
  • Code assistant tools
  • Research‑grade Q&A

Who it’s for. Developers and researchers needing a large, open‑source LLM for local inference. The model is suitable for teams that can allocate sufficient GPU memory and prefer a permissive MIT license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.3 GB 13.3 GB
Too big Get file →
Q3_K_S14.4 GB 15.4 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 →
Q4_K_S18.7 GB 19.7 GB
Too big Get file →
Q4_K_M19.7 GB 20.7 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 →
Q6_K26.7 GB 27.7 GB
Too big Get file →
Q8_034.6 GB 35.6 GB
Too big Get file →
F1665.1 GB (2 parts) 66.2 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (12.29 GB file, ~13.3 GB VRAM). For 16 GB VRAM, Q4_K_M (19.68 GB file, ~20.7 GB VRAM) is a good balance. For 24 GB VRAM, Q5_K_M (23.1 GB file, ~24.1 GB VRAM) offers higher quality. Estimates are approximate.

What GPU do you need for THUDM/GLM-4-32B-Base-0414?

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: the best quant that fits is Q3_K_S (14.4 GB file, about 15.4 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 (26.7 GB file, about 27.7 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 THUDM/GLM-4-32B-Base-0414 quant should you choose?

Q4_K_M is the usual starting point for THUDM/GLM-4-32B-Base-0414: 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 Q2_K at 12.3 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 byDevQuasar-12
FamilyGLM
Licensemit
Downloads (HF)443
Last updated2025-04-16

Frequently asked questions about THUDM/GLM-4-32B-Base-0414

How much VRAM does THUDM/GLM-4-32B-Base-0414 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 THUDM/GLM-4-32B-Base-0414 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of THUDM/GLM-4-32B-Base-0414 GGUF?

It depends on the quant: Q2_K is 12.3 GB, Q3_K_S is 14.4 GB, Q3_K_M is 15.9 GB, Q3_K_L is 17.2 GB, Q4_K_S is 18.7 GB, Q4_K_M is 19.7 GB and 5 more.

What context length does THUDM/GLM-4-32B-Base-0414 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 THUDM/GLM-4-32B-Base-0414 GGUF?

The files are on Hugging Face in the DevQuasar-12/THUDM.GLM-4-32B-Base-0414-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 THUDM/GLM-4-32B-Base-0414 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‑4‑32B‑Base‑0414 on 8 GB VRAM?

Use the Q2_K quantized file; it requires about 13.3 GB VRAM at 8 k context.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of GLM-4-32B-Base-0414

Similar models

Browse all →

More from DevQuasar-12

All by DevQuasar-12 →

More GLM models

All GLM →

Other medium models

All medium models →