GL

glm-4-9b-chat-1m

GLMGGUF by ZeroWwUpdated 2024-07-13
Download on Hugging Face
Parameters9.48B
Context1024K
Layers40
Architecturechatglm
Smallest quant8.8 GB
Quick answer

glm-4-9b-chat-1m needs about 11.3 GB of memory at its main file (a 10.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 8.8 GB (Q5_K) to 19.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

glm-4-9b-chat-1m is a 9.48B-parameter GLM model in GGUF format, quantized by ZeroWw. Its trained context length is 1024K tokens. The repository has 5 quant files, from 8.8 GB (Q5_K) to 19.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K8.8 GB 9.9 GB
Too big Get file →
Q6_K9.8 GB 11.0 GB
Too big Get file →
—10.1 GB 11.3 GB
Too big Get file →
Q8_011.2 GB 12.4 GB
Too big Get file →
F1619.0 GB 20.1 GB
Too big Get file →

What GPU do you need for glm-4-9b-chat-1m?

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: the best quant that fits is the main file (10.1 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.2 GB file, about 12.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (19.0 GB file, about 20.1 GB in use).

Which glm-4-9b-chat-1m quant should you choose?

If memory is tight, the smallest file is Q5_K at 8.8 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturechatglm
Parameters9.48B
Layers40
Trained context1,048,576 tokens
KV cache (fp16)80 KB per token

Source

Quantized byZeroWw
FamilyGLM
Licensemit
Downloads (HF)84
Last updated2024-07-13

Frequently asked questions about glm-4-9b-chat-1m

How much VRAM does glm-4-9b-chat-1m need?

About 11.3 GB at its main file with an 8K context window. That is the 10.1 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-4-9b-chat-1m on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of glm-4-9b-chat-1m GGUF?

It depends on the quant: Q5_K is 8.8 GB, Q6_K is 9.8 GB, file is 10.1 GB, Q8_0 is 11.2 GB, F16 is 19.0 GB.

What context length does glm-4-9b-chat-1m support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download glm-4-9b-chat-1m GGUF?

The files are on Hugging Face in the ZeroWw/glm-4-9b-chat-1m-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-4-9b-chat-1m 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.

Similar models

Browse all →

More from ZeroWw

All by ZeroWw →

More GLM models

All GLM →

Other small models

All small models →