GL

ERNIE 21B A3B GLM 4.7 Flash Thinking

GLMGGUF by yyblUpdated 2026-02-21
Download on Hugging Face
Parameters21.8B
Context128K
Layers28
Architectureernie4_5-moe
Smallest quant23.2 GB
Quick answer

ERNIE 21B A3B GLM 4.7 Flash Thinking needs about 24.2 GB of memory at Q8_0 (a 23.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

ERNIE 21B A3B GLM 4.7 Flash Thinking is a 21.8B-parameter GLM model in GGUF format, quantized by yybl. Its trained context length is 128K tokens. The repository has 1 quant file, from 23.2 GB (Q8_0) to 23.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_023.2 GB 24.2 GB
Too big Get file →

What GPU do you need for ERNIE 21B A3B GLM 4.7 Flash Thinking?

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: the best quant that fits is Q8_0 (23.2 GB file, about 24.2 GB in use).

Which ERNIE 21B A3B GLM 4.7 Flash Thinking quant should you choose?

Q8_0 (23.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureernie4_5-moe
Parameters21.8B (approximate, mixture of experts)
Active parameters3B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byyybl
FamilyGLM
Licenseapache-2.0
Downloads (HF)26
Last updated2026-02-21

Frequently asked questions about ERNIE 21B A3B GLM 4.7 Flash Thinking

How much VRAM does ERNIE 21B A3B GLM 4.7 Flash Thinking need?

About 24.2 GB at Q8_0 with an 8K context window. That is the 23.2 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 ERNIE 21B A3B GLM 4.7 Flash Thinking on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ERNIE 21B A3B GLM 4.7 Flash Thinking GGUF?

It depends on the quant: Q8_0 is 23.2 GB.

What context length does ERNIE 21B A3B GLM 4.7 Flash Thinking support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download ERNIE 21B A3B GLM 4.7 Flash Thinking GGUF?

The files are on Hugging Face in the yybl/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-Q8_0-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 ERNIE 21B A3B GLM 4.7 Flash Thinking use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of ERNIE-21B-A3B-GLM-4.7-Flash-Thinking

Similar models

Browse all →

More from yybl

All by yybl →

More GLM models

All GLM →

Other medium models

All medium models →