Ornith 1.5 122B needs about 80.2 GB of memory at Q4_K_M (a 78.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 0.7 GB to 249.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
Ornith 1.5 122B – a 125B MOE model with vision and MTP support
Ornith 1.5 122B is a 125B parameter mixture‑of‑experts model based on qwen35moe. It supports text and image input and includes Multi‑Token Prediction layers. The model is released under the MIT license and is available in many GGUF quantizations.
Good at
- Large context handling – 262144 tokens
- Vision input via mmproj files
- MTP for speculative decoding
Limits
- Requires large VRAM for full precision – 250.7 GB at 8k context
- No native support for audio or video
- License is MIT – no commercial restrictions
Best for
- Edge deployment with low‑precision quants
- Multimodal chat with image understanding
- Research on MOE architectures
Who it’s for. Developers building multimodal applications that need large context and vision. Researchers exploring mixture‑of‑experts models and speculative decoding. Teams that can allocate high‑memory GPUs for full‑precision usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.7 GB | 2.0 GB | Fits | Get file → | |
| IQ1_S | 30.0 GB | 31.3 GB | Too big | Get file → | |
| IQ1_M | 33.2 GB | 34.5 GB | Too big | Get file → | |
| IQ2_XXS | 38.3 GB | 39.6 GB | Too big | Get file → | |
| IQ2_XS | 40.0 GB | 41.3 GB | Too big | Get file → | |
| IQ2_S | 42.5 GB | 43.8 GB | Too big | Get file → | |
| IQ2_M | 46.4 GB | 47.7 GB | Too big | Get file → | |
| Q2_K | 48.9 GB | 50.3 GB | Too big | Get file → | |
| IQ3_XXS | 54.4 GB (2 parts) | 55.7 GB | Too big | Get file → | |
| Q3_K_S | 57.5 GB (2 parts) | 58.8 GB | Too big | Get file → | |
| IQ3_XS | 57.9 GB (2 parts) | 59.2 GB | Too big | Get file → | |
| Q3_K_M | 60.6 GB (2 parts) | 61.9 GB | Too big | Get file → | |
| Q3_K_L | 64.2 GB (2 parts) | 65.5 GB | Too big | Get file → | |
| IQ3_M | 67.6 GB (2 parts) | 69.0 GB | Too big | Get file → | |
| IQ4_XS | 70.2 GB (2 parts) | 71.5 GB | Too big | Get file → | |
| Q4_0 | 71.3 GB (2 parts) | 72.6 GB | Too big | Get file → | |
| Q4_K_S | 74.2 GB (2 parts) | 75.5 GB | Too big | Get file → | |
| Q4_1 | 78.5 GB (2 parts) | 79.8 GB | Too big | Get file → | |
| IQ4_NL | 78.9 GB (2 parts) | 80.2 GB | Too big | Get file → | |
| Q4_K_M | 78.9 GB (2 parts) | 80.2 GB | Too big | Get file → | |
| Q4_K_L | 84.7 GB (3 parts) | 86.0 GB | Too big | Get file → | |
| Q5_K_S | 89.1 GB (3 parts) | 90.4 GB | Too big | Get file → | |
| Q5_K_M | 94.9 GB (3 parts) | 96.3 GB | Too big | Get file → | |
| Q6_K_S | 104.4 GB (3 parts) | 105.7 GB | Too big | Get file → | |
| Q6_K | 109.3 GB (3 parts) | 110.6 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 Q4_K_M (78.92 GB file, 80.2 GB memory at 8k context). For 16 GB VRAM, Q4_K_L (84.72 GB file, 86 GB memory). For 32 GB VRAM, Q5_K_M (94.94 GB file, 96.3 GB memory). Larger VRAM allows higher‑quality quants like Q6_K or BF16.
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: the best quant that fits is the main file (0.7 GB file, about 2.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 2.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 2.0 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 2.0 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 2.0 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 2.0 GB in use).
- 32 GB VRAM: the best quant that fits is IQ1_S (30.0 GB file, about 31.3 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (46.4 GB file, about 47.7 GB in use).
Which Ornith 1.5 122B quant should you choose?
Q4_K_M is the usual starting point for Ornith 1.5 122B: it balances file size and quality well. Here it is a 78.9 GB file.
The Q8_0 file is 132.6 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 the first one in the table at 0.7 GB, with the quality trade-offs that come with fewer bits.
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 80.2 GB at Q4_K_M with an 8K context window. That is the 78.9 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?
Yes, with the smaller files: the 0.7 GB file needs about 2.0 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 GGUF?
It depends on the quant: file is 0.7 GB, IQ1_S is 30.0 GB, IQ1_M is 33.2 GB, IQ2_XXS is 38.3 GB, IQ2_XS is 40.0 GB, IQ2_S is 42.5 GB and 21 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 bartowski/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 a single 8 GB GPU?
No, the smallest quant requires 78.92 GB of VRAM at 8k context. A 8 GB GPU cannot run any quant of this model.
Does the model support image input?
Yes, image input is supported via mmproj files that pair with any quant.
What is the context length of this model?
The model was trained on 262144 tokens and can handle that context length.