GL

Glyph

GLMGGUF by MungertUpdated 2025-11-01
Download on Hugging Face
Parameters9.4B
Context128K
Layers40
Architectureglm4
Smallest quant0.0 GB
Quick answer

Glyph needs about 7.5 GB of memory at Q4_K_M (a 6.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 27 quants, from 0.0 GB to 18.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.3 GB.

Glyph: a 9.4B GLM-4 VLM with 64k context and visual‑text compression

Glyph is a 9.4B‑parameter GLM‑4 VLM built on GLM‑4.1V‑9B‑Base. It supports 64k token context and processes long text via visual‑text compression. The model is open‑source under the MIT license.

Good at

  • Long‑context reasoning
  • Vision‑language tasks
  • Multimodal compression

Limits

  • No native vision support in GGUF
  • Requires 64k context to use full capability
  • No explicit language list

Best for

  • Chatbots needing long context
  • Multimodal agents
  • Research on visual‑text compression

Who it’s for. Developers and researchers building multimodal applications that require extended context windows. The model is suitable for those who can manage the memory requirements and are comfortable with the MIT license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.8 GB
Fits Get file →
IQ1_S3.3 GB 4.1 GB
Fits Get file →
IQ1_M3.6 GB 4.4 GB
Fits Get file →
IQ2_XXS3.7 GB 4.6 GB
Fits Get file →
IQ2_XS3.9 GB 4.7 GB
Fits Get file →
IQ2_S3.9 GB 4.8 GB
Fits Get file →
Q2_K_S4.0 GB 4.8 GB
Fits Get file →
IQ2_M4.1 GB 4.9 GB
Fits Get file →
Q2_K_M4.1 GB 5.0 GB
Fits Get file →
IQ3_XXS4.5 GB 5.4 GB
Fits Get file →
IQ3_XS4.6 GB 5.5 GB
Fits Get file →
Q3_K_S4.7 GB 5.6 GB
Fits Get file →
IQ3_M4.9 GB 5.7 GB
Fits Get file →
Q3_K_M5.2 GB 6.0 GB
Fits Get file →
IQ4_NL5.3 GB 6.1 GB
Fits Get file →
IQ4_XS5.4 GB 6.3 GB
Fits Get file →
Q4_05.9 GB 6.8 GB
Fits Get file →
Q4_K_S5.9 GB 6.8 GB
Fits Get file →
Q4_16.0 GB 6.8 GB
Fits Get file →
Q4_K_M6.6 GB 7.5 GB
Tight Get file →
Q5_06.9 GB 7.8 GB
Tight Get file →
Q5_17.5 GB 8.3 GB
Too big Get file →
Q5_K_M7.5 GB 8.3 GB
Too big Get file →
Q6_K_M8.6 GB 9.4 GB
Too big Get file →
Q8_010.0 GB 10.8 GB
Too big Get file →
F1613.9 GB 14.8 GB
Too big Get file →
BF1618.8 GB 19.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 3.29 GB, memory 4.1 GB) or IQ1_M (3.59 GB, 4.4 GB). For 16 GB VRAM, Q4_K_M (6.64 GB, 7.5 GB) or Q5_0 (6.94 GB, 7.8 GB) are suitable. For 32 GB VRAM, Q6_K_M (8.57 GB, 9.4 GB) or Q8_0 (10 GB, 10.8 GB) provide higher precision.

What GPU do you need for Glyph?

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 (0.0 GB file, about 0.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (5.2 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_0 (6.9 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (10.0 GB file, about 10.8 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (13.9 GB file, about 14.8 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (18.8 GB file, about 19.6 GB in use).

Which Glyph quant should you choose?

Q4_K_M is the usual starting point for Glyph: it balances file size and quality well. Here it is a 6.6 GB file.

The Q8_0 file is 10.0 GB, about 1.5 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 0.0 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

Architectureglm4
Parameters9.4B
Layers40
Trained context131,072 tokens
KV cache (fp16)40 KB per token

Source

Quantized byMungert
FamilyGLM
Licensemit
Downloads (HF)961
Last updated2025-11-01

Frequently asked questions about Glyph

How much VRAM does Glyph need?

About 7.5 GB at Q4_K_M with an 8K context window. That is the 6.6 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 Glyph on an 8 GB GPU?

Yes, with Q5_0: the 6.9 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Glyph GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.6 GB, IQ2_XXS is 3.7 GB, IQ2_XS is 3.9 GB, IQ2_S is 3.9 GB and 21 more.

What context length does Glyph support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.3 GB at 32K.

Where can I download Glyph GGUF?

The files are on Hugging Face in the Mungert/Glyph-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 Glyph 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 Glyph on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations keeps VRAM usage under 8 GB.

Does Glyph support vision tasks?

Glyph is a VLM, but the GGUF files do not include native vision support; use external vision pipelines.

Other GGUFs of GLM-4.1V-9B-Base

Similar models

Browse all →

More from Mungert

All by Mungert →

More GLM models

All GLM →

Other small models

All small models →