GL

Glm Edge 4b Chat

GLMGGUF by zai-orgUpdated 2024-11-28
Download on Hugging Face
Parameters4.33B
Context3K
Layers40
Architecturechatglm
Smallest quant2.5 GB
Quick answer

Glm Edge 4b Chat needs about 4.1 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 13 quants, from 2.5 GB (Q4_0) to 8.7 GB (F16).

GLM-Edge 4B Chat, a compact chat model with 3072 token context

GLM-Edge 4B Chat is a 4‑billion‑parameter chat model based on the chatglm architecture. It supports a 3072‑token context window and is available in multiple GGUF quantizations. The model is released under a non‑specified license.

Good at

  • Chat‑style dialogue
  • Fast inference on modest GPUs
  • Low memory footprint with Q4 variants

Limits

  • No vision support
  • License not specified
  • Limited to 3072 token context

Best for

  • Lightweight chatbots
  • Rapid prototyping on 8‑GB VRAM
  • Embedded LLM applications

Who it’s for. Developers needing a small, chat‑optimized model for local deployment. Suitable for edge devices or quick experimentation where GPU memory is constrained.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.5 GB 3.4 GB
Fits Get file →
Q4_K_S2.5 GB 3.4 GB
Fits Get file →
Q4_K2.6 GB 3.5 GB
Fits Get file →
Q4_K_M2.6 GB 3.5 GB
Fits Get file →
Q4_12.7 GB 3.6 GB
Fits Get file →
Q5_03.0 GB 3.9 GB
Fits Get file →
Q5_K_S3.0 GB 3.9 GB
Fits Get file →
Q5_K3.1 GB 4.0 GB
Fits Get file →
Q5_K_M3.1 GB 4.0 GB
Fits Get file →
Q5_13.3 GB 4.1 GB
Fits Get file →
Q6_K3.6 GB 4.4 GB
Fits Get file →
Q8_04.6 GB 5.5 GB
Fits Get file →
F168.7 GB 9.5 GB
Too big Get file →

For 8‑GB VRAM, Q4_0 or Q4_K_S (~4 GB memory) is recommended. If 12‑GB VRAM is available, Q5_K_M or Q5_1 (~4.6–4.8 GB) offers better quality. Higher precision Q6_K or Q8_0 requires 5–6 GB memory and gives improved accuracy.

What GPU do you need for Glm Edge 4b Chat?

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 Q4_K_S (2.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.6 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (8.7 GB file, about 10.2 GB in use).

Which Glm Edge 4b Chat quant should you choose?

Q4_K_M is the usual starting point for Glm Edge 4b Chat: it balances file size and quality well. Here it is a 2.6 GB file.

The Q8_0 file is 4.6 GB, about 1.8 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 Q4_0 at 2.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturechatglm
Parameters4.33B
Layers40
Trained context3,072 tokens
KV cache (fp16)120 KB per token

Source

Quantized byzai-org
FamilyGLM
Licenseother
Downloads (HF)3,202
Last updated2024-11-28

Frequently asked questions about Glm Edge 4b Chat

How much VRAM does Glm Edge 4b Chat need?

About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.6 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 Glm Edge 4b Chat on an 8 GB GPU?

Yes, with Q8_0: the 4.6 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Glm Edge 4b Chat GGUF?

It depends on the quant: Q4_0 is 2.5 GB, Q4_K_S is 2.5 GB, Q4_K is 2.6 GB, Q4_K_M is 2.6 GB, Q4_1 is 2.7 GB, Q5_0 is 3.0 GB and 7 more.

What context length does Glm Edge 4b Chat support?

The GGUF header lists a trained context length of 3,072 tokens (3K). The KV cache grows with the context you use: about 1.0 GB at 8K and 0.4 GB at 3K.

Where can I download Glm Edge 4b Chat GGUF?

The files are on Hugging Face in the zai-org/glm-edge-4b-chat-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 Edge 4b Chat use?

Hugging Face lists the license as other. 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 Edge 4b Chat on 8 GB VRAM?

Yes, the Q4_0 or Q4_K_S quantizations use about 4 GB of VRAM at 8k context, fitting within an 8‑GB GPU.

Does this model support image inputs?

No, the model has no vision capabilities and only processes text.

What is the maximum context length?

The model was trained with a 3072‑token context window and supports up to that length.

Similar models

Browse all →

More from zai-org

All by zai-org →

More GLM models

All GLM →

Other small models

All small models →