Abliterated needs about 11.1 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 9.0 GB (Q4_K_M) to 29.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
14.8B Qwen2.5 Coder model in GGUF format
Abliterated is a 14.8B parameter Qwen2.5 Coder model fine‑tuned for coding and tool usage. It supports a 32768 token context window and is distributed under the agpl-3.0 license. The model is available in multiple GGUF quantizations.
Good at
- coding tasks
- tool integration
- large context handling
Limits
- no vision support
- agpl-3.0 license restrictions
- requires 8k context for estimates
Best for
- code generation
- debugging assistance
- API tool chaining
Who it’s for. Developers and researchers needing a large‑parameter coding model with extended context. Suitable for local deployment via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 9.0 GB | 11.1 GB | Too big | Get file → | |
| Q6_K | 12.1 GB | 14.2 GB | Too big | Get file → | |
| Q8_0 | 15.7 GB | 17.8 GB | Too big | Get file → | |
| — | 29.5 GB | 31.7 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K_M quant (8.99 GB file, ~11.1 GB memory at 8k context). For 12 GB VRAM, Q6_K (12.12 GB file, ~14.2 GB memory). Larger VRAM allows Q8_0 or the unknown quant.
What GPU do you need for 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: the best quant that fits is Q4_K_M (9.0 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.7 GB file, about 17.8 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (29.5 GB file, about 31.7 GB in use).
Which Abliterated quant should you choose?
Q4_K_M is the usual starting point for Abliterated: it balances file size and quality well. Here it is a 9.0 GB file.
The Q8_0 file is 15.7 GB, about 1.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Abliterated
How much VRAM does Abliterated need?
About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.0 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 Abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Abliterated GGUF?
It depends on the quant: Q4_K_M is 9.0 GB, Q6_K is 12.1 GB, Q8_0 is 15.7 GB, file is 29.5 GB.
What context length does 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 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Abliterated GGUF?
The files are on Hugging Face in the criscar22/Qwen2.5-Coder-14B-Instruct-abliterated repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Abliterated use?
Hugging Face lists the license as agpl-3.0. 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 Abliterated on 8 GB VRAM?
Yes, the Q4_K_M quant uses 8.99 GB file size and requires about 11.1 GB memory at 8k context, which fits 8 GB VRAM with some overhead.
Does Abliterated support vision?
No, the model only supports text and coding tasks.