GL

LongWriter Glm4 9b

GLMGGUF by bartowskiUpdated 2024-10-19
Download on Hugging Face
Parameters9.4B
Context1024K
Layers40
Architecturechatglm
Smallest quant3.9 GB
Quick answer

LongWriter Glm4 9b needs about 7.1 GB of memory at Q4_K_M (a 6.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 3.9 GB (IQ2_M) to 18.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.3 GB.

LongWriter GLM4 9b – a 9.4B parameter chat model with 1M token context

LongWriter GLM4 9b is a 9.4B parameter chat model based on the GLM family. It supports a trained context of 1,048,576 tokens and is released under the apache-2.0 license. The model is available in multiple GGUF quantizations for llama.cpp.

Good at

  • Large context handling
  • Chat-oriented responses
  • Flexible quantization options

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Large VRAM needed for higher quants

Best for

  • Long-form content generation
  • Extended conversation threads
  • Research prototyping

Who it’s for. Developers and researchers who need a large-context chat model and can manage the memory requirements. The model is suitable for those using llama.cpp or LM Studio for local inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M3.9 GB 4.8 GB
Fits Get file →
Q2_K4.0 GB 4.8 GB
Fits Get file →
IQ3_XS4.4 GB 5.3 GB
Fits Get file →
Q3_K_S4.6 GB 5.4 GB
Fits Get file →
Q2_K_L4.6 GB 5.4 GB
Fits Get file →
IQ3_M4.8 GB 5.6 GB
Fits Get file →
Q3_K_M5.1 GB 5.9 GB
Fits Get file →
IQ4_XS5.3 GB 6.1 GB
Fits Get file →
Q3_K_L5.3 GB 6.1 GB
Fits Get file →
Q4_05.5 GB 6.3 GB
Fits Get file →
Q4_05.5 GB 6.3 GB
Fits Get file →
Q4_05.5 GB 6.3 GB
Fits Get file →
Q4_05.5 GB 6.3 GB
Fits Get file →
Q4_K_S5.8 GB 6.6 GB
Fits Get file →
Q3_K_XL5.8 GB 6.7 GB
Fits Get file →
Q4_K_M6.3 GB 7.1 GB
Fits Get file →
Q5_K_S6.7 GB 7.5 GB
Tight Get file →
Q4_K_L6.7 GB 7.5 GB
Tight Get file →
Q5_K_M7.1 GB 8.0 GB
Tight Get file →
Q5_K_L7.5 GB 8.4 GB
Too big Get file →
Q6_K8.3 GB 9.1 GB
Too big Get file →
Q6_K_L8.6 GB 9.4 GB
Too big Get file →
Q8_010.0 GB 10.8 GB
Too big Get file →
F1618.8 GB 19.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 5.46 GB, ~6.3 GB memory). For 12 GB VRAM, Q4_K_M (6.25 GB, ~7.1 GB memory) or Q5_K_S (6.69 GB, ~7.5 GB memory). For 16 GB VRAM, Q6_K (8.26 GB, ~9.1 GB memory) or Q6_K_L (8.56 GB, ~9.4 GB memory).

What GPU do you need for LongWriter Glm4 9b?

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: the best quant that fits is Q3_K_M (5.1 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (7.1 GB file, about 8.0 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 Q8_0 (10.0 GB file, about 10.8 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (18.8 GB file, about 19.6 GB in use).

Which LongWriter Glm4 9b quant should you choose?

Q4_K_M is the usual starting point for LongWriter Glm4 9b: it balances file size and quality well. Here it is a 6.3 GB file.

The Q8_0 file is 10.0 GB, about 1.6 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 IQ2_M at 3.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturechatglm
Parameters9.4B
Layers40
Trained context1,048,576 tokens
KV cache (fp16)40 KB per token

Source

Quantized bybartowski
FamilyGLM
Licenseapache-2.0
Downloads (HF)2,398
Last updated2024-10-19

Frequently asked questions about LongWriter Glm4 9b

How much VRAM does LongWriter Glm4 9b need?

About 7.1 GB at Q4_K_M with an 8K context window. That is the 6.3 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 LongWriter Glm4 9b on an 8 GB GPU?

Yes, with Q5_K_M: the 7.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LongWriter Glm4 9b GGUF?

It depends on the quant: IQ2_M is 3.9 GB, Q2_K is 4.0 GB, IQ3_XS is 4.4 GB, Q3_K_S is 4.6 GB, Q2_K_L is 4.6 GB, IQ3_M is 4.8 GB and 18 more.

What context length does LongWriter Glm4 9b 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 0.3 GB at 8K and 1.3 GB at 32K.

Where can I download LongWriter Glm4 9b GGUF?

The files are on Hugging Face in the bartowski/LongWriter-glm4-9b-abliterated-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 LongWriter Glm4 9b 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 LongWriter GLM4 9b on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires about 6.3 GB of VRAM at 8k context.

Does this model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of LongWriter-glm4-9b-abliterated

Similar models

Browse all →

More from bartowski

All by bartowski →

More GLM models

All GLM →

Other small models

All small models →