phi 4 abliterated Orion 18B i1 needs about 13.7 GB of memory at Q4_K_M (a 11.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 4.0 GB (IQ1_S) to 14.8 GB (Q6_K).
Phi‑4 Abliterated Orion 18B i1 – 18.1B‑parameter Phi‑3 architecture
Phi‑4 Abliterated Orion 18B i1 is a 18.1B‑parameter Phi‑3 model based on the Orion‑abliterated family. It supports a 16384‑token context window and is distributed as GGUF files quantized by mradermacher. The model is licensed under GPL‑3.0.
Good at
- Long‑form storytelling
- Complex emotional dialogue
- Reasoning under constraints
Limits
- No vision support
- GPL‑3.0 license restricts commercial use
- Large VRAM required for higher‑quality quants
Best for
- Narrative generation on local GPU
- Interactive fiction engines
- Research on large‑context LLMs
Who it’s for. Developers and researchers who need a large Phi‑3 variant for local inference. The model is suitable for those who can run GGUF files with llama.cpp and have sufficient VRAM for the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.0 GB | 6.6 GB | Fits | Get file → | |
| IQ1_M | 4.4 GB | 7.0 GB | Fits | Get file → | |
| IQ2_XXS | 5.0 GB | 7.6 GB | Tight | Get file → | |
| IQ2_XS | 5.5 GB | 8.1 GB | Too big | Get file → | |
| IQ2_S | 5.8 GB | 8.4 GB | Too big | Get file → | |
| IQ2_M | 6.2 GB | 8.8 GB | Too big | Get file → | |
| Q2_K_S | 6.3 GB | 8.9 GB | Too big | Get file → | |
| Q2_K | 6.8 GB | 9.4 GB | Too big | Get file → | |
| IQ3_XXS | 7.2 GB | 9.8 GB | Too big | Get file → | |
| IQ3_XS | 7.7 GB | 10.2 GB | Too big | Get file → | |
| IQ3_S | 8.0 GB | 10.6 GB | Too big | Get file → | |
| Q3_K_S | 8.0 GB | 10.6 GB | Too big | Get file → | |
| IQ3_M | 8.5 GB | 11.1 GB | Too big | Get file → | |
| Q3_K_M | 9.0 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_L | 9.8 GB | 12.3 GB | Too big | Get file → | |
| IQ4_XS | 9.8 GB | 12.3 GB | Too big | Get file → | |
| IQ4_NL | 10.3 GB | 12.9 GB | Too big | Get file → | |
| Q4_0 | 10.3 GB | 12.9 GB | Too big | Get file → | |
| Q4_K_S | 10.4 GB | 13.0 GB | Too big | Get file → | |
| Q4_K_M | 11.1 GB | 13.7 GB | Too big | Get file → | |
| Q4_1 | 11.4 GB | 14.0 GB | Too big | Get file → | |
| Q5_K_S | 12.5 GB | 15.1 GB | Too big | Get file → | |
| Q5_K_M | 13.1 GB | 15.7 GB | Too big | Get file → | |
| Q6_K | 14.8 GB | 17.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (4.01 GB, 6.6 GB memory). With 12 GB VRAM, IQ4_K_M (11.14 GB, 13.7 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (13.06 GB, 15.7 GB memory) offers higher quality while staying within limits. Estimates are approximate.
What GPU do you need for phi 4 abliterated Orion 18B i1?
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: the best quant that fits is IQ2_XXS (5.0 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_M (9.0 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (13.1 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (14.8 GB file, about 17.4 GB in use).
Which phi 4 abliterated Orion 18B i1 quant should you choose?
Q4_K_M is the usual starting point for phi 4 abliterated Orion 18B i1: it balances file size and quality well. Here it is a 11.1 GB file.
If memory is tight, the smallest file is IQ1_S at 4.0 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 phi 4 abliterated Orion 18B i1
How much VRAM does phi 4 abliterated Orion 18B i1 need?
About 13.7 GB at Q4_K_M with an 8K context window. That is the 11.1 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 phi 4 abliterated Orion 18B i1 on an 8 GB GPU?
Yes, with IQ2_XXS: the 5.0 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi 4 abliterated Orion 18B i1 GGUF?
It depends on the quant: IQ1_S is 4.0 GB, IQ1_M is 4.4 GB, IQ2_XXS is 5.0 GB, IQ2_XS is 5.5 GB, IQ2_S is 5.8 GB, IQ2_M is 6.2 GB and 18 more.
What context length does phi 4 abliterated Orion 18B i1 support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.1 GB at 8K and 4.2 GB at 16K.
Where can I download phi 4 abliterated Orion 18B i1 GGUF?
The files are on Hugging Face in the mradermacher/phi-4-abliterated-Orion-18B-i1-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 phi 4 abliterated Orion 18B i1 use?
Hugging Face lists the license as gpl-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 this model on 8 GB VRAM?
Yes, the IQ1_S quant requires 4.01 GB file size and about 6.6 GB VRAM at 8k context.
Does this model support vision?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under GPL‑3.0, which restricts commercial use.