Abliterated needs about 17.7 GB of memory at Q4_K_M (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 0.1 GB to 25.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Abliterated: a 24B‑parameter reasoning model with 2B active parameters
Abliterated is a 24.0B‑parameter Mixture‑of‑Experts model built on LFM2.5‑24B‑A2B. It has 2.45B active parameters and a context length of 131,072 tokens. The model is designed for fast, private on‑device reasoning and tool‑calling.
Good at
- Fast on‑device reasoning
- Efficient tool‑calling
- Large context handling
Limits
- No vision support
- Requires large VRAM for higher quants
- License is other
Best for
- Private agent reasoning
- Tool‑enabled chatbots
- On‑device inference
Who it’s for. Developers building private agents that need strong reasoning and tool‑calling capabilities on local hardware. The model is suitable for users who can manage the memory requirements of the larger quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 3.2 GB | Fits | Get file → | |
| IQ2_XXS | 7.5 GB | 10.7 GB | Too big | Get file → | |
| IQ3_XXS | 9.0 GB | 12.1 GB | Too big | Get file → | |
| Q3_K_XL | 10.9 GB | 14.1 GB | Too big | Get file → | |
| Q4_K_M | 14.5 GB | 17.7 GB | Too big | Get file → | |
| Q8_0 | 25.5 GB | 28.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (file size 7.47 GB, estimated 10.7 GB memory). For 16 GB VRAM, IQ3_XXS (8.96 GB, 12.1 GB memory) or Q3_K_XL (10.95 GB, 14.1 GB memory). For 32 GB VRAM, Q4_K_M (14.53 GB, 17.7 GB memory) or Q8_0 (25.49 GB, 28.7 GB memory).
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: the best quant that fits is the main file (0.1 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.2 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_XXS (7.5 GB file, about 10.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_XL (10.9 GB file, about 14.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (14.5 GB file, about 17.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.5 GB file, about 28.7 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 14.5 GB file.
The Q8_0 file is 25.5 GB, about 1.8 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.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Abliterated
How much VRAM does Abliterated need?
About 17.7 GB at Q4_K_M with an 8K context window. That is the 14.5 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?
Yes, with the smaller files: the 0.1 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Abliterated GGUF?
It depends on the quant: file is 0.1 GB, IQ2_XXS is 7.5 GB, IQ3_XXS is 9.0 GB, Q3_K_XL is 10.9 GB, Q4_K_M is 14.5 GB, Q8_0 is 25.5 GB.
What context length does Abliterated support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Abliterated GGUF?
The files are on Hugging Face in the alexwkleung/LFM2.5-24B-A2B-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 Abliterated 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.
Can I run Abliterated on 8 GB VRAM?
Yes, using the IQ2_XXS quantization which requires approximately 10.7 GB of VRAM at 8 k context.
Does Abliterated support vision?
No, Abliterated is a text‑only model and does not support vision.
What is the context length of Abliterated?
The model supports a context length of 131,072 tokens.