wp qwen3.6 35b a3b wp judge v4 needs about 17.8 GB of memory at IQ4_XS (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 12.9 GB (IQ3_XXS) to 25.3 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
WP Judge v4 – an open‑weight WordPress PHP code reviewer
WP Judge v4 is a Qwen3.6‑35B‑A3B based model that critiques WordPress PHP functions. It evaluates compliance, safety, performance, and other quality dimensions. The model is fine‑tuned for code review, not code generation.
Good at
- PHP code critique
- Security and SQL safety checks
- Performance and API usage analysis
Limits
- No code generation
- No vision support
- Requires 8k context for best performance
Best for
- Automated code review pipelines
- CI/CD quality gates
- Developer feedback tools
Who it’s for. Developers and teams that need automated, consistent reviews of WordPress PHP code. It is suitable for integration into CI/CD workflows or as a standalone reviewer.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 12.9 GB | 14.0 GB | Too big | Get file → | |
| IQ4_XS | 16.6 GB | 17.8 GB | Too big | Get file → | |
| Q6_K | 25.2 GB | 26.4 GB | Too big | Get file → | |
| Q5_K_M | 25.3 GB | 26.5 GB | Too big | Get file → |
For 8 GB VRAM, use the IQ4_XS file (16.58 GB). For 12 GB VRAM, use IQ3_XXS (12.87 GB). For larger GPUs, Q6_K or Q5_K_M (25.2 GB and 25.35 GB) provide higher precision. Memory estimates are approximate.
What GPU do you need for wp qwen3.6 35b a3b wp judge v4?
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: the best quant that fits is IQ3_XXS (12.9 GB file, about 14.0 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (16.6 GB file, about 17.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (25.3 GB file, about 26.5 GB in use).
Which wp qwen3.6 35b a3b wp judge v4 quant should you choose?
IQ4_XS (16.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ3_XXS at 12.9 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 wp qwen3.6 35b a3b wp judge v4
How much VRAM does wp qwen3.6 35b a3b wp judge v4 need?
About 17.8 GB at IQ4_XS with an 8K context window. That is the 16.6 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 wp qwen3.6 35b a3b wp judge v4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of wp qwen3.6 35b a3b wp judge v4 GGUF?
It depends on the quant: IQ3_XXS is 12.9 GB, IQ4_XS is 16.6 GB, Q6_K is 25.2 GB, Q5_K_M is 25.3 GB.
What context length does wp qwen3.6 35b a3b wp judge v4 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download wp qwen3.6 35b a3b wp judge v4 GGUF?
The files are on Hugging Face in the iamchum/wp-qwen3.6-35b-a3b-wp-judge-v4-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 wp qwen3.6 35b a3b wp judge v4 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.
Can I run WP Judge v4 on 8 GB VRAM?
Yes, the IQ4_XS quantized file is 16.58 GB and requires about 17.8 GB of VRAM at 8k context.
Does this model generate code?
No, WP Judge v4 only critiques existing PHP code. Use the base Qwen3.6‑35B‑A3B for code generation.
What context length does it support?
It was trained on 262144 tokens and works best with an 8k context window.