GL

GLM-4.7-Flash

GLMGGUF by MungertUpdated 2026-01-28
Download on Hugging Face
Parameters30B
Context198K
Layers47
Architecturedeepseek2
Smallest quant0.1 GB
Quick answer

GLM-4.7-Flash needs about 19.8 GB of memory at Q4_K_M (a 18.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 35 quants, from 0.1 GB to 59.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

GLM-4.7-Flash, a 30B-A3B MoE model for efficient local deployment

GLM-4.7-Flash is a 30B-A3B Mixture of Experts model based on the deepseek2 architecture. It supports 202,752 context tokens and is released under the MIT license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • MoE efficiency
  • Flexible quantization

Limits

  • Requires high VRAM for full precision
  • No vision support
  • Limited language metadata

Best for

  • Local inference with limited GPU
  • Research on MoE models
  • Fine‑tuning with custom data

Who it’s for. Developers and researchers who need a large‑scale MoE model that can run on local hardware. The model is suitable for those who can manage the memory requirements and want to experiment with different quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.4 GB
Fits Get file →
IQ1_S9.0 GB 10.4 GB
Too big Get file →
IQ2_XXS9.7 GB 11.0 GB
Too big Get file →
IQ1_M9.9 GB 11.2 GB
Too big Get file →
IQ2_XS10.8 GB 12.1 GB
Too big Get file →
IQ2_S10.8 GB 12.1 GB
Too big Get file →
IQ2_M11.3 GB 12.7 GB
Too big Get file →
Q2_K_M11.9 GB 13.2 GB
Too big Get file →
IQ3_XXS13.4 GB 14.7 GB
Too big Get file →
IQ3_XS13.4 GB 14.8 GB
Too big Get file →
IQ3_M15.0 GB 16.3 GB
Too big Get file →
IQ3_S15.0 GB 16.3 GB
Too big Get file →
Q3_K_M15.5 GB 16.9 GB
Too big Get file →
IQ4_XS16.0 GB 17.4 GB
Too big Get file →
Q4_016.9 GB 18.2 GB
Too big Get file →
IQ4_NL17.0 GB 18.3 GB
Too big Get file →
Q4_017.2 GB 18.5 GB
Too big Get file →
Q4_K_S17.8 GB 19.1 GB
Too big Get file →
Q4_K_M18.5 GB 19.8 GB
Too big Get file →
Q4_K_L18.6 GB 19.9 GB
Too big Get file →
Q4_118.7 GB 20.1 GB
Too big Get file →
Q4_119.0 GB 20.4 GB
Too big Get file →
Q5_020.6 GB 22.0 GB
Too big Get file →
Q5_020.9 GB 22.2 GB
Too big Get file →
Q5_K_M21.8 GB 23.2 GB
Too big Get file →
Q5_K_L22.0 GB 23.3 GB
Too big Get file →
Q5_122.5 GB 23.8 GB
Too big Get file →
Q5_122.7 GB 24.0 GB
Too big Get file →
Q6_K_M24.6 GB 26.0 GB
Too big Get file →
Q6_K_L24.8 GB 26.1 GB
Too big Get file →
Q8_031.8 GB 33.2 GB
Too big Get file →
BF1638.1 GB 39.4 GB
Too big Get file →
F1638.1 GB 39.4 GB
Too big Get file →
BF1659.9 GB (2 parts) 61.2 GB
Too big Get file →
F1659.9 GB (2 parts) 61.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 16.87 GB, memory 18.2 GB) or Q4_K_S (file size 17.77 GB, memory 19.1 GB). For 12 GB VRAM, Q4_K_M (file size 18.45 GB, memory 19.8 GB) or Q5_0 (file size 20.62 GB, memory 22 GB) are suitable. Higher VRAM allows Q6_K_M (file size 24.61 GB, memory 26 GB) or Q8_0 (file size 31.84 GB, memory 33.2 GB).

What GPU do you need for GLM-4.7-Flash?

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: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ1_M (9.9 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (13.4 GB file, about 14.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_1 (22.7 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (24.8 GB file, about 26.1 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (38.1 GB file, about 39.4 GB in use).

Which GLM-4.7-Flash quant should you choose?

Q4_K_M is the usual starting point for GLM-4.7-Flash: it balances file size and quality well. Here it is a 18.5 GB file.

The Q8_0 file is 31.8 GB, about 1.7 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 the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters30B (approximate, mixture of experts)
Layers47
Trained context202,752 tokens
KV cache (fp16)100 KB per token

Source

Quantized byMungert
FamilyGLM
Licensemit
Downloads (HF)1,405
Last updated2026-01-28

Frequently asked questions about GLM-4.7-Flash

How much VRAM does GLM-4.7-Flash need?

About 19.8 GB at Q4_K_M with an 8K context window. That is the 18.5 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 on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GLM-4.7-Flash GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 9.0 GB, IQ2_XXS is 9.7 GB, IQ1_M is 9.9 GB, IQ2_XS is 10.8 GB, IQ2_S is 10.8 GB and 29 more.

What context length does GLM-4.7-Flash 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 GGUF?

The files are on Hugging Face in the Mungert/GLM-4.7-Flash-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 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-4.7-Flash on 8 GB VRAM?

The Q4_0 quantization requires approximately 18.2 GB VRAM at 8 k context, so 8 GB VRAM is insufficient.

What is the smallest quantization available?

The smallest file is the unknown quant at 0.07 GB, but its memory usage is 1.4 GB at 8 k context.

Is the model licensed for commercial use?

The model is released under the MIT license, which allows commercial use.

Similar models

Browse all →

More from Mungert

All by Mungert →

More GLM models

All GLM →

Other medium models

All medium models →