WizardLM 33B V1.0 Uncensored needs about 27.7 GB of memory at IQ3_S (a 14.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 13.3 GB (IQ3_XS) to 34.6 GB (Q8_0).
WizardLM 33B V1.0 Uncensored is a 32.5B-parameter Wizardlm model in GGUF format, quantized by altomek. Its trained context length is 2K tokens. The repository has 4 quant files, from 13.3 GB (IQ3_XS) to 34.6 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 13.3 GB | 17.1 GB | Too big | Get file → | |
| IQ3_S | 14.1 GB | 17.8 GB | Too big | Get file → | |
| IQ3_M | 14.9 GB | 18.7 GB | Too big | Get file → | |
| Q8_0 | 34.6 GB | 38.3 GB | Too big | Get file → |
What GPU do you need for WizardLM 33B V1.0 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 IQ3_M (14.9 GB file, about 28.5 GB in use).
- 48 GB VRAM: the best quant that fits is IQ3_M (14.9 GB file, about 28.5 GB in use).
Which WizardLM 33B V1.0 Uncensored quant should you choose?
IQ3_S (14.1 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.
If memory is tight, the smallest file is IQ3_XS at 13.3 GB, with the quality trade-offs that come with fewer bits. 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
Source
Frequently asked questions about WizardLM 33B V1.0 Uncensored
How much VRAM does WizardLM 33B V1.0 Uncensored need?
About 27.7 GB at IQ3_S with an 8K context window. That is the 14.1 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 WizardLM 33B V1.0 Uncensored on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of WizardLM 33B V1.0 Uncensored GGUF?
It depends on the quant: IQ3_XS is 13.3 GB, IQ3_S is 14.1 GB, IQ3_M is 14.9 GB, Q8_0 is 34.6 GB.
What context length does WizardLM 33B V1.0 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 WizardLM 33B V1.0 Uncensored GGUF?
The files are on Hugging Face in the altomek/WizardLM-33B-V1.0-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 WizardLM 33B V1.0 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.