GL

GLM 4.7 Flash MTP

GLMGGUF by giocomUpdated 2026-08-05
Download on Hugging Face
Parameters1.91B
Context198K
Layers48
Architecturedeepseek2
Smallest quant1.2 GB
Quick answer

GLM 4.7 Flash MTP needs about 2.6 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.2 GB (Q4_K_M) to 3.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

GLM 4.7 Flash MTP – 1.91B parameter MoE model

GLM 4.7 Flash MTP is a 1.91B parameter model in the GLM family, built on the deepseek2 architecture. It supports a 202752 token context window and is released under the apache-2.0 license.

Good at

  • Large context inference
  • Efficient MoE deployment
  • Stable performance on 8k token prompts

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache-2.0

Best for

  • Chat applications needing long context
  • Local deployment with limited VRAM
  • Research on MoE models

Who it’s for. Developers and researchers looking for a lightweight MoE model with a large context window. The model is suitable for local inference using llama.cpp, vLLM, or SGLang.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.2 GB 2.6 GB
Fits Get file →
Q8_02.0 GB 3.4 GB
Fits Get file →
BF163.8 GB 5.2 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (1.22 GB file, 2.6 GB memory at 8k context) is recommended. Q8_0 (2.04 GB file, 3.4 GB memory) fits 12 GB VRAM. BF16 (3.83 GB file, 5.2 GB memory) requires 16 GB VRAM or more.

What GPU do you need for GLM 4.7 Flash MTP?

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 Q8_0 (2.0 GB file, about 3.4 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (3.8 GB file, about 5.2 GB in use).

Which GLM 4.7 Flash MTP quant should you choose?

Q4_K_M is the usual starting point for GLM 4.7 Flash MTP: it balances file size and quality well. Here it is a 1.2 GB file.

The Q8_0 file is 2.0 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters1.91B (approximate, mixture of experts)
Layers48
Trained context202,752 tokens
KV cache (fp16)102 KB per token

Source

Quantized bygiocom
FamilyGLM
Licenseapache-2.0
Downloads (HF)455
Last updated2026-08-05

Frequently asked questions about GLM 4.7 Flash MTP

How much VRAM does GLM 4.7 Flash MTP need?

About 2.6 GB at Q4_K_M with an 8K context window. That is the 1.2 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 GLM 4.7 Flash MTP on an 8 GB GPU?

Yes, with BF16: the 3.8 GB file needs about 5.2 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 MTP GGUF?

It depends on the quant: Q4_K_M is 1.2 GB, Q8_0 is 2.0 GB, BF16 is 3.8 GB.

What context length does GLM 4.7 Flash MTP support?

The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.4 GB at 32K.

Where can I download GLM 4.7 Flash MTP GGUF?

The files are on Hugging Face in the giocom/GLM-4.7-Flash-MTP-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 MTP 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.

Can I run GLM 4.7 Flash MTP on 8 GB VRAM?

Yes, using the Q4_K_M quantization which uses 2.6 GB memory at 8k context.

Does this model support vision tasks?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of GLM-4.7-Flash

Similar models

Browse all →

More from giocom

All by giocom →

More GLM models

All GLM →

Other tiny models

All tiny models →