WI

ehartford_wizard-vicuna-30b-uncensored

WizardGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters32.5B
Context2K
Layers60
Architecturellama
Smallest quant13.5 GB
Quick answer

ehartford_wizard-vicuna-30b-uncensored needs about 33.2 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 13.5 GB (Q2_K) to 34.6 GB (Q8_0).

Wizard‑Vicuna‑30B‑Uncensored – a large uncensored LLM in GGUF format

Wizard‑Vicuna‑30B‑Uncensored is a 30 billion‑parameter model based on the Wizard family and the llama architecture. It is released in multiple GGUF quantisations and can be run with llama.cpp or compatible libraries. The model is uncensored and requires users to handle content responsibly.

Good at

  • Large context handling up to 2048 tokens
  • High‑capacity language generation
  • Uncensored content generation

Limits

  • No alignment guardrails
  • Requires significant VRAM for higher quants
  • No vision support

Best for

  • Research on uncensored language models
  • Fine‑tuning with custom RLHF LoRA
  • Testing model safety boundaries

Who it’s for. Developers and researchers who need a large, uncensored LLM for experimentation or custom alignment. The model is suitable for those who can manage the responsibility of unfiltered content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.5 GB 17.3 GB
Too big Get file →
Q3_K_S14.1 GB 17.8 GB
Too big Get file →
Q3_K_M15.8 GB 19.5 GB
Too big Get file →
Q3_K_L17.3 GB 21.1 GB
Too big Get file →
Q4_018.4 GB 22.1 GB
Too big Get file →
Q4_K_S18.4 GB 22.2 GB
Too big Get file →
Q4_K_M19.6 GB 23.4 GB
Too big Get file →
Q5_022.4 GB 26.2 GB
Too big Get file →
Q5_K_S22.4 GB 26.2 GB
Too big Get file →
Q5_K_M23.0 GB 26.8 GB
Too big Get file →
Q6_K26.7 GB 30.5 GB
Too big Get file →
Q8_034.6 GB 38.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 19.62 GB, estimated memory 33.2 GB). For 12 GB VRAM, Q5_K_M (23.05 GB, 36.6 GB). For 16 GB VRAM, Q6_K (26.69 GB, 40.3 GB). These estimates are approximate.

What GPU do you need for ehartford_wizard-vicuna-30b-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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q4_K_S (18.4 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 40.3 GB in use).

Which ehartford_wizard-vicuna-30b-uncensored quant should you choose?

Q4_K_M is the usual starting point for ehartford_wizard-vicuna-30b-uncensored: it balances file size and quality well. Here it is a 19.6 GB file.

The Q8_0 file is 34.6 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 Q2_K at 13.5 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
Parameters32.5B
Layers60
Trained context2,048 tokens
KV cache (fp16)1560 KB per token

Source

Quantized byTheBloke
FamilyWizard
Licenseother
Downloads (HF)3,989
Last updated2023-09-27

Frequently asked questions about ehartford_wizard-vicuna-30b-uncensored

How much VRAM does ehartford_wizard-vicuna-30b-uncensored need?

About 33.2 GB at Q4_K_M with an 8K context window. That is the 19.6 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 ehartford_wizard-vicuna-30b-uncensored on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ehartford_wizard-vicuna-30b-uncensored GGUF?

It depends on the quant: Q2_K is 13.5 GB, Q3_K_S is 14.1 GB, Q3_K_M is 15.8 GB, Q3_K_L is 17.3 GB, Q4_0 is 18.4 GB, Q4_K_S is 18.4 GB and 6 more.

What context length does ehartford_wizard-vicuna-30b-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 13.1 GB at 8K and 3.3 GB at 2K.

Where can I download ehartford_wizard-vicuna-30b-uncensored GGUF?

The files are on Hugging Face in the TheBloke/Wizard-Vicuna-30B-Uncensored-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 ehartford_wizard-vicuna-30b-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 Wizard‑Vicuna‑30B‑Uncensored on 8 GB VRAM?

Only with the lowest quants such as Q2_K or Q3_K_S, but memory usage will still exceed 8 GB. It is not recommended for 8 GB VRAM.

Does this model support vision tasks?

No, the model has no vision capability.

What license applies to this model?

The model is released under an 'other' license; review the source repo for details.

Other GGUFs of Wizard-Vicuna-30B-Uncensored

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Wizard models

All Wizard →

Other medium models

All medium models →