LFM2.5 8B A1B Uncensored needs about 7.3 GB of memory at Q4_K_M (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 11 quants, from 3.2 GB (Q2_K) to 16.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
LFM2.5 8B A1B Uncensored – a decensored LFM2 MoE model
LFM2.5 8B A1B Uncensored is a 8.47 billion‑parameter LFM2 MoE model with 1 billion active parameters per token. It is a Heretic‑abliterated version of LiquidAI/LFM2.5‑8B‑A1B, removing safety alignment while preserving most original behavior. The model supports 128 000‑token context.
Good at
- Large context handling
- MoE efficient inference
- Uncensored content generation
Limits
- Requires recent llama.cpp with LFM2 MoE support
- No vision capability
- License is other (not specified)
Best for
- Chat applications needing long context
- Research on uncensored language models
- Testing safety alignment removal
Who it’s for. Developers and researchers who need a large‑context, uncensored LFM2 MoE model and have access to a recent llama.cpp build. The model is suitable for experimentation with safety ablation techniques.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.2 GB | 5.3 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 4.6 GB | 6.7 GB | Fits | Get file → | |
| Q4_K_S | 4.9 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.2 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_S | 5.9 GB | 8.0 GB | Tight | Get file → | |
| Q5_K_M | 6.0 GB | 8.1 GB | Too big | Get file → | |
| Q6_K | 7.0 GB | 9.1 GB | Too big | Get file → | |
| Q8_0 | 9.0 GB | 11.1 GB | Too big | Get file → | |
| BF16 | 16.9 GB | 19.1 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (5.16 GB) or Q5_K_S (5.87 GB) are recommended. With 12 GB VRAM, Q5_K_M (6.03 GB) or Q6_K (6.96 GB) provide higher fidelity. Larger quants such as Q8_0 (9.01 GB) need 16 GB VRAM or more.
What GPU do you need for LFM2.5 8B A1B Uncensored?
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: the best quant that fits is Q3_K_S (3.8 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_S (5.9 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.9 GB file, about 19.1 GB in use).
Which LFM2.5 8B A1B Uncensored quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 8B A1B Uncensored: it balances file size and quality well. Here it is a 5.2 GB file.
The Q8_0 file is 9.0 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.
If memory is tight, the smallest file is Q2_K at 3.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2.5 8B A1B Uncensored
How much VRAM does LFM2.5 8B A1B Uncensored need?
About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.2 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 LFM2.5 8B A1B Uncensored on an 8 GB GPU?
Yes, with Q5_K_S: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 8B A1B Uncensored GGUF?
It depends on the quant: Q2_K is 3.2 GB, Q3_K_S is 3.8 GB, Q3_K_M is 4.1 GB, IQ4_XS is 4.6 GB, Q4_K_S is 4.9 GB, Q4_K_M is 5.2 GB and 5 more.
What context length does LFM2.5 8B A1B Uncensored support?
The GGUF header lists a trained context length of 128,000 tokens (125K). 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 LFM2.5 8B A1B Uncensored GGUF?
The files are on Hugging Face in the zaakirio/LFM2.5-8B-A1B-Uncensored-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 LFM2.5 8B A1B Uncensored 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 this model on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_S quantizations, which require approximately 5–6 GB VRAM at 8 k context.
Does this model support vision tasks?
No, the model has no vision capability.
What is the maximum context length?
The model was trained with 128 000 tokens and supports that context length.