WI

WizardLM-2-7B-abliterated

WizardlmGGUF by aaronday3Updated 2024-05-27
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.5 GB
Quick answer

WizardLM-2-7B-abliterated needs about 5.1 GB of memory at Q3_K_M (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

WizardLM-2-7B-abliterated is a 7.24B-parameter Wizardlm model in GGUF format, quantized by aaronday3. Its trained context length is 32K tokens. The repository has 1 quant file, from 3.5 GB (Q3_K_M) to 3.5 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M3.5 GB 5.1 GB
Fits Get file →

What GPU do you need for WizardLM-2-7B-abliterated?

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 (3.5 GB file, about 5.1 GB in use).

Which WizardLM-2-7B-abliterated quant should you choose?

Q3_K_M (3.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byaaronday3
FamilyWizardlm
Licenseapache-2.0
Downloads (HF)30
Last updated2024-05-27

Frequently asked questions about WizardLM-2-7B-abliterated

How much VRAM does WizardLM-2-7B-abliterated need?

About 5.1 GB at Q3_K_M with an 8K context window. That is the 3.5 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 WizardLM-2-7B-abliterated on an 8 GB GPU?

Yes, with Q3_K_M: the 3.5 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of WizardLM-2-7B-abliterated GGUF?

It depends on the quant: Q3_K_M is 3.5 GB.

What context length does WizardLM-2-7B-abliterated support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download WizardLM-2-7B-abliterated GGUF?

The files are on Hugging Face in the aaronday3/WizardLM-2-7B-abliterated-Q3_K_M-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 WizardLM-2-7B-abliterated 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.

Similar models

Browse all →

More from aaronday3

All by aaronday3 →

More Wizardlm models

All Wizardlm →

Other small models

All small models →