LFM2.5 230M distilled Gemini 3.8 Flash Uncensored needs about 1.1 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.1 GB (IQ3_S) to 0.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
230M‑parameter distilled Gemini 3.8 Flash model with reduced refusal behavior
LFM2.5 230M distilled Gemini 3.8 Flash Uncensored is a small on‑device model built with distillation from Gemini 3.8 Flash and abliteration to suppress refusals. It retains reasoning and tool usage abilities while operating with modest memory footprints.
Good at
- Reasoning
- Tool usage
- Low‑latency inference
Limits
- Reduced safety alignment
- No vision support
- Limited long‑generation coherence
Best for
- Edge device inference
- Rapid prototyping
- Low‑cost reasoning tasks
Who it’s for. Developers needing a compact, fast model for reasoning tasks who are aware of its reduced safety alignment. Suitable for internal tooling where compliance with safety guidelines is managed separately.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 0.1 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_M | 0.2 GB | 1.1 GB | Fits | Get file → | |
| Q6_K | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q8_0 | 0.2 GB | 1.2 GB | Fits | Get file → | |
| F16 | 0.5 GB | 1.4 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (0.15 GB) or Q5_K_M (0.17 GB) are recommended. If more RAM is available, Q6_K (0.19 GB) or Q8_0 (0.25 GB) offer higher quality. F16 (0.46 GB) provides the best fidelity but requires more memory.
What GPU do you need for LFM2.5 230M distilled Gemini 3.8 Flash 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: the best quant that fits is F16 (0.5 GB file, about 1.4 GB in use).
Which LFM2.5 230M distilled Gemini 3.8 Flash Uncensored quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 230M distilled Gemini 3.8 Flash Uncensored: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.2 GB, about 1.6 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 IQ3_S at 0.1 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
Frequently asked questions about LFM2.5 230M distilled Gemini 3.8 Flash Uncensored
How much VRAM does LFM2.5 230M distilled Gemini 3.8 Flash Uncensored need?
About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.2 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 230M distilled Gemini 3.8 Flash Uncensored on an 8 GB GPU?
Yes, with F16: the 0.5 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 230M distilled Gemini 3.8 Flash Uncensored GGUF?
It depends on the quant: IQ3_S is 0.1 GB, Q4_K_M is 0.2 GB, Q5_K_M is 0.2 GB, Q6_K is 0.2 GB, Q8_0 is 0.2 GB, F16 is 0.5 GB.
What context length does LFM2.5 230M distilled Gemini 3.8 Flash 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 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download LFM2.5 230M distilled Gemini 3.8 Flash Uncensored GGUF?
The files are on Hugging Face in the Null-Guard/LFM2.5-230M-distilled-Gemini-3.8-Flash-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 230M distilled Gemini 3.8 Flash Uncensored 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?
Yes, the Q4_K_M and Q5_K_M quantizations fit comfortably on 8 GB VRAM with an estimated 1.1 GB memory usage at 8 k context.
Does this model support vision?
No, it is a text‑only model with no vision capabilities.
What license applies to this model?
The model is released under Apache‑2.0, but the base model license may differ; check the base license before redistribution.