WizardCoder 33B V1.1 needs about 29.9 GB of memory at Q6_K (a 27.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 27.4 GB (Q6_K) to 35.4 GB (Q8_0).
WizardCoder 33B V1.1 is a 33.3B-parameter Wizardcoder model in GGUF format, quantized by tsqn. Its trained context length is 16K tokens. The repository has 2 quant files, from 27.4 GB (Q6_K) to 35.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 27.4 GB (6 parts) | 29.9 GB | Too big | Get file → | |
| Q8_0 | 35.4 GB (8 parts) | 38.0 GB | Too big | Get file → |
What GPU do you need for WizardCoder 33B V1.1?
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 Q6_K (27.4 GB file, about 29.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.4 GB file, about 38.0 GB in use).
Which WizardCoder 33B V1.1 quant should you choose?
Q6_K (27.4 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about WizardCoder 33B V1.1
How much VRAM does WizardCoder 33B V1.1 need?
About 29.9 GB at Q6_K with an 8K context window. That is the 27.4 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 WizardCoder 33B V1.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of WizardCoder 33B V1.1 GGUF?
It depends on the quant: Q6_K is 27.4 GB, Q8_0 is 35.4 GB.
What context length does WizardCoder 33B V1.1 support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.1 GB at 8K and 4.2 GB at 16K.
Where can I download WizardCoder 33B V1.1 GGUF?
The files are on Hugging Face in the tsqn/WizardCoder-33B-V1.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.