WI

WizardLM-13B-Uncensored

WizardlmGGUF by duyntnetUpdated 2024-05-20
Download on Hugging Face
Parameters13B
Context2K
Layers40
Architecturellama
Smallest quant2.9 GB
Quick answer

WizardLM-13B-Uncensored needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 27 quants, from 2.9 GB (IQ1_S) to 13.8 GB (Q8_0).

WizardLM‑13B‑Uncensored, 13B llama‑style model without built‑in alignment

WizardLM‑13B‑Uncensored is a 13‑billion‑parameter llama architecture model. It was trained on a subset of data with alignment responses removed, providing an uncensored base for custom alignment. The model supports a 2048‑token context window.

Good at

  • Large‑scale text generation
  • Custom alignment via LoRA
  • Flexible fine‑tuning

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • License is other, not open source

Best for

  • Research on alignment techniques
  • Developing custom chatbots
  • Testing policy‑free language models

Who it’s for. Developers and researchers who need a large, uncensored language model to add their own alignment layers. The model is suitable for experimentation and building specialized applications where guardrails are applied separately.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.9 GB 5.1 GB
Fits Get file →
IQ1_M3.1 GB 5.3 GB
Fits Get file →
IQ2_XXS3.5 GB 5.7 GB
Fits Get file →
IQ2_XS3.9 GB 6.1 GB
Fits Get file →
IQ2_S4.2 GB 6.4 GB
Fits Get file →
Q2_K_S4.4 GB 6.6 GB
Fits Get file →
IQ2_M4.5 GB 6.7 GB
Fits Get file →
Q2_K4.9 GB 7.0 GB
Fits Get file →
IQ3_XXS5.0 GB 7.1 GB
Fits Get file →
IQ3_XS5.4 GB 7.5 GB
Tight Get file →
IQ3_S5.7 GB 7.8 GB
Tight Get file →
Q3_K_S5.7 GB 7.8 GB
Tight Get file →
IQ3_M6.0 GB 8.2 GB
Too big Get file →
Q3_K_M6.3 GB 8.5 GB
Too big Get file →
Q3_K_L6.9 GB 9.1 GB
Too big Get file →
IQ4_XS7.0 GB 9.1 GB
Too big Get file →
IQ4_NL7.4 GB 9.5 GB
Too big Get file →
Q4_07.4 GB 9.6 GB
Too big Get file →
Q4_K_S7.4 GB 9.6 GB
Too big Get file →
Q4_K_M7.9 GB 10.0 GB
Too big Get file →
Q4_18.2 GB 10.3 GB
Too big Get file →
Q5_K_S9.0 GB 11.2 GB
Too big Get file →
Q5_09.0 GB 11.2 GB
Too big Get file →
Q5_K_M9.2 GB 11.4 GB
Too big Get file →
Q5_19.8 GB 12.0 GB
Too big Get file →
Q6_K10.7 GB 12.9 GB
Too big Get file →
Q8_013.8 GB 16.0 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (2.9 GB) or IQ1_M (3.14 GB). For 12‑GB VRAM, Q3_K_S (5.66 GB) or Q3_K_M (6.34 GB) are suitable. For 16‑GB VRAM, Q5_K_S (8.97 GB) or Q5_0 (8.99 GB) provide a balance of size and performance. Memory estimates are approximate.

What GPU do you need for WizardLM-13B-Uncensored?

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 IQ2_M (4.5 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (8.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which WizardLM-13B-Uncensored quant should you choose?

Q4_K_M is the usual starting point for WizardLM-13B-Uncensored: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 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 IQ1_S at 2.9 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

Architecturellama
Parameters13B
Layers40
Trained context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized byduyntnet
FamilyWizardlm
Licenseother
Downloads (HF)1,223
Last updated2024-05-20

Frequently asked questions about WizardLM-13B-Uncensored

How much VRAM does WizardLM-13B-Uncensored need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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-13B-Uncensored on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WizardLM-13B-Uncensored GGUF?

It depends on the quant: IQ1_S is 2.9 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.2 GB, Q2_K_S is 4.4 GB and 21 more.

What context length does WizardLM-13B-Uncensored support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download WizardLM-13B-Uncensored GGUF?

The files are on Hugging Face in the duyntnet/WizardLM-13B-Uncensored-imatrix-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-13B-Uncensored 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 WizardLM‑13B‑Uncensored on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantizations, which are 2.9 GB and 3.14 GB respectively.

Does this model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The license is listed as "other" and is not an open‑source license.

Similar models

Browse all →

More from duyntnet

All by duyntnet →

More Wizardlm models

All Wizardlm →

Other medium models

All medium models →