GL

GLM 4.7 Flash 18B A3B

GLMGGUF by lovedheartUpdated 2026-01-22
Download on Hugging Face
Parameters19.5B
Context198K
Layers47
Architecturedeepseek2
Smallest quant10.8 GB
Quick answer

GLM 4.7 Flash 18B A3B needs about 15.1 GB of memory at MXFP4_MOE (a 13.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 10.8 GB (Q2_K) to 39.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

GLM 4.7 Flash 18B A3B is a 19.5B-parameter GLM model in GGUF format, quantized by lovedheart. Its trained context length is 198K tokens. The repository has 4 quant files, from 10.8 GB (Q2_K) to 39.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.8 GB 12.1 GB
Too big Get file →
MXFP4_MOE13.7 GB 15.1 GB
Too big Get file →
Q4_K14.3 GB 15.6 GB
Too big Get file →
BF1639.1 GB 40.4 GB
Too big Get file →

What GPU do you need for GLM 4.7 Flash 18B A3B?

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 Q4_K (14.3 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K (14.3 GB file, about 15.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K (14.3 GB file, about 15.6 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (39.1 GB file, about 40.4 GB in use).

Which GLM 4.7 Flash 18B A3B quant should you choose?

MXFP4_MOE (13.7 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is Q2_K at 10.8 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

Architecturedeepseek2
Parameters19.5B (approximate, mixture of experts)
Active parameters3B
Layers47
Trained context202,752 tokens
KV cache (fp16)100 KB per token

Source

Quantized bylovedheart
FamilyGLM
Licensemit
Downloads (HF)227
Last updated2026-01-22

Frequently asked questions about GLM 4.7 Flash 18B A3B

How much VRAM does GLM 4.7 Flash 18B A3B need?

About 15.1 GB at MXFP4_MOE with an 8K context window. That is the 13.7 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 4.7 Flash 18B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 4.7 Flash 18B A3B GGUF?

It depends on the quant: Q2_K is 10.8 GB, MXFP4_MOE is 13.7 GB, Q4_K is 14.3 GB, BF16 is 39.1 GB.

What context length does GLM 4.7 Flash 18B A3B support?

The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.4 GB at 32K.

Where can I download GLM 4.7 Flash 18B A3B GGUF?

The files are on Hugging Face in the lovedheart/GLM-4.7-Flash-18B-A3B-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 4.7 Flash 18B A3B 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.

Other GGUFs of GLM-4.7-Flash

Similar models

Browse all →

More from lovedheart

All by lovedheart →

More GLM models

All GLM →

Other medium models

All medium models →