Ornith 1.5 122B UNCENSORED needs about 80.7 GB of memory at Q4_K_M (a 79.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 1.0 GB (Q8_0) to 79.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
122B MOE model with vision and self‑speculative decoding
Ornith 1.5 122B UNCENSORED is a Qwen3.5‑based MOE model with 122 billion parameters and 10 billion active. It supports vision (image and video) and includes a native MTP speculative decoding head. The GGUF build contains two quantizations: Q4_K_M (~79 GB) and IQ2_XXS (~44 GB).
Good at
- Vision tasks with mmproj tower
- Self‑speculative decoding via MTP
- Large context up to 262 144 tokens
Limits
- Requires 2.3 GB VRAM for Q8_0 at 8 k context
- Large file sizes limit deployment on low‑end hardware
- Uncensored content – not for end‑user deployment without safety controls
Best for
- Edge‑deployable vision‑enabled inference
- High‑throughput single‑GPU inference with MTP
- Research on MOE and self‑improvement loops
Who it’s for. Developers and researchers needing a large‑scale vision‑capable model for experimentation. The uncensored nature requires additional safety layers before consumer deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 1.0 GB | 2.3 GB | Fits | Get file → | |
| IQ2_XXS | 44.1 GB | 45.4 GB | Too big | Get file → | |
| Q4_K_M | 79.4 GB | 80.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M; it needs about 80.7 GB of RAM at 8 k context, which is beyond typical consumer GPUs. The IQ2_XXS quant (~45.4 GB RAM) fits 48 GB consumer boxes and is the smallest available. Q8_0 is the smallest file but still requires 2.3 GB VRAM at 8 k context.
What GPU do you need for Ornith 1.5 122B 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 Q8_0 (1.0 GB file, about 2.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (1.0 GB file, about 2.3 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (1.0 GB file, about 2.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (1.0 GB file, about 2.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (1.0 GB file, about 2.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (1.0 GB file, about 2.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (1.0 GB file, about 2.3 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_XXS (44.1 GB file, about 45.4 GB in use).
Which Ornith 1.5 122B UNCENSORED quant should you choose?
Q4_K_M is the usual starting point for Ornith 1.5 122B UNCENSORED: it balances file size and quality well. Here it is a 79.4 GB file.
The Q8_0 file is 1.0 GB, about 0.0 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 Q8_0 at 1.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornith 1.5 122B UNCENSORED
How much VRAM does Ornith 1.5 122B UNCENSORED need?
About 80.7 GB at Q4_K_M with an 8K context window. That is the 79.4 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 Ornith 1.5 122B UNCENSORED on an 8 GB GPU?
Yes, with Q8_0: the 1.0 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ornith 1.5 122B UNCENSORED GGUF?
It depends on the quant: Q8_0 is 1.0 GB, IQ2_XXS is 44.1 GB, Q4_K_M is 79.4 GB.
What context length does Ornith 1.5 122B UNCENSORED support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.3 GB at 32K.
Where can I download Ornith 1.5 122B UNCENSORED GGUF?
The files are on Hugging Face in the dealignai/Ornith-1.5-122B-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 Ornith 1.5 122B UNCENSORED use?
Hugging Face lists the license as mit. 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 Ornith 1.5 122B UNCENSORED on 8 GB VRAM?
No. The smallest quant requires 2.3 GB VRAM at 8 k context, but the model’s memory footprint is large; typical 8 GB GPUs cannot handle it.
Does this model support image input?
Yes. It includes an mmproj vision tower that preserves VL capability identical to the base BF16 source.
Is the model safe for public deployment?
No. The uncensored build removes refusal logic; it should not be deployed to end users without additional safety controls.