Ornith 1.5 122B needs about 61.1 GB of memory at Q3_K_XL (a 59.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 40.4 GB (IQ1_M) to 249.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
122B MOE model with vision support, efficient single‑GPU deployment
Ornith 1.5 122B is a 122‑billion‑parameter mixture of experts model built on the qwen35moe architecture. It supports vision tasks and is optimized for single‑GPU and edge deployment. The model is released under the MIT license.
Good at
- Vision‑enabled reasoning
- Efficient single‑GPU inference
- Edge‑deployable quantized variants
Limits
- Large context size requires high VRAM
- No explicit language list provided
- Requires quantization for practical use
Best for
- Vision‑based question answering
- Edge device inference with quantized model
- Single‑GPU research prototyping
Who it’s for. Developers needing a large‑scale vision‑capable model that can run on a single GPU or mobile device. Researchers and hobbyists who prefer an open‑source, MIT‑licensed model with a mixture‑of‑experts architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 40.4 GB | 41.7 GB | Too big | Get file → | |
| IQ2_XXS | 42.0 GB | 43.3 GB | Too big | Get file → | |
| Q2_K_XL | 44.5 GB | 45.9 GB | Too big | Get file → | |
| IQ3_XXS | 49.5 GB | 50.8 GB | Too big | Get file → | |
| Q3_K_XL | 59.8 GB (3 parts) | 61.1 GB | Too big | Get file → | |
| Q4_K_XL | 79.7 GB (3 parts) | 81.0 GB | Too big | Get file → | |
| Q5_K_XL | 94.6 GB (3 parts) | 95.9 GB | Too big | Get file → | |
| Q6_K_XL | 114.2 GB (4 parts) | 115.5 GB | Too big | Get file → | |
| Q8_0 | 132.6 GB (4 parts) | 133.9 GB | Too big | Get file → | |
| BF16 | 249.4 GB (7 parts) | 250.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (40.36 GB file, ~41.7 GB memory at 8k context). For 16 GB VRAM, Q4_K_XL (79.71 GB file, ~81 GB memory) or Q5_K_XL (94.61 GB file, ~95.9 GB memory). For 32 GB VRAM, Q6_K_XL (114.22 GB file, ~115.5 GB memory) or Q8_0 (132.56 GB file, ~133.9 GB memory).
What GPU do you need for Ornith 1.5 122B?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q2_K_XL (44.5 GB file, about 45.9 GB in use).
Which Ornith 1.5 122B quant should you choose?
Q3_K_XL (59.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ1_M at 40.4 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 Ornith 1.5 122B
How much VRAM does Ornith 1.5 122B need?
About 61.1 GB at Q3_K_XL with an 8K context window. That is the 59.8 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 41.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.5 122B GGUF?
It depends on the quant: IQ1_M is 40.4 GB, IQ2_XXS is 42.0 GB, Q2_K_XL is 44.5 GB, IQ3_XXS is 49.5 GB, Q3_K_XL is 59.8 GB, Q4_K_XL is 79.7 GB and 4 more.
What context length does Ornith 1.5 122B 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 GGUF?
The files are on Hugging Face in the unsloth/Ornith-1.5-122B-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 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 on 8 GB VRAM?
Use the IQ1_M quantization; it requires about 41.7 GB of VRAM at 8k context, so 8 GB is insufficient without further optimization.
Does this model support vision tasks?
Yes, the model has detected vision abilities and can process image inputs.
What license applies to Ornith 1.5 122B?
The model is released under the MIT license.