Qwen2.5 Coder 32B Abliterated needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Qwen2.5 Coder 32B Abliterated – uncensored 32B coding model
Qwen2.5 Coder 32B Abliterated is a 32.8B parameter model built on the Qwen architecture. It removes refusal behavior while maintaining coding performance. The GGUF Q4_K_M build is 19.85 GB and runs on a single 24 GB GPU.
Good at
- Coding tasks
- Uncensored code generation
- Local agent work
Limits
- Requires 24 GB VRAM for Q4_K_M
- No vision support
- License is Apache‑2.0
Best for
- Local coding assistant
- Security research and red‑team coding
- Exploit analysis
Who it’s for. Developers and researchers who need a local coding assistant without refusal constraints. The model is suitable for environments where uncensored code generation is required, but users must comply with applicable law.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 19.9 GB | 22.5 GB | Too big | Get file → |
The only available quant is Q4_K_M, 19.85 GB. It requires about 22.5 GB VRAM at 8 k context. If you have a 24 GB GPU, this build will fit. No other quants are provided, so use the Q4_K_M file for deployment.
What GPU do you need for Qwen2.5 Coder 32B Abliterated?
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: the best quant that fits is Q4_K_M (19.9 GB file, about 22.5 GB in use).
Which Qwen2.5 Coder 32B Abliterated quant should you choose?
Q4_K_M is the usual starting point for Qwen2.5 Coder 32B Abliterated: it balances file size and quality well. Here it is a 19.9 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Qwen2.5 Coder 32B Abliterated
How much VRAM does Qwen2.5 Coder 32B Abliterated need?
About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 Qwen2.5 Coder 32B Abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen2.5 Coder 32B Abliterated GGUF?
It depends on the quant: Q4_K_M is 19.9 GB.
What context length does Qwen2.5 Coder 32B Abliterated support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Qwen2.5 Coder 32B Abliterated GGUF?
The files are on Hugging Face in the TobiasLogic/Qwen2.5-Coder-32B-abliterated-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 Qwen2.5 Coder 32B Abliterated 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 this model on 8 GB VRAM?
No. The Q4_K_M build needs about 22.5 GB VRAM at 8 k context, so 8 GB is insufficient.
Does the model support vision?
No. The model has no vision capability.
What license applies to this model?
Apache‑2.0, inherited from the base model.