Ornith 1.5 122B needs about 77.2 GB of memory at Q4_K_M (a 75.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 75.8 GB (Q4_K_M) 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 122B MOE model for efficient single‑GPU and edge deployment
Ornith 1.5 122B is a 122B mixture‑of‑experts model built on the qwen35moe architecture. It supports vision tasks and is optimized for single‑GPU use. The model is released under the MIT license and can be run with various GGUF quantizations.
Good at
- Vision‑enabled inference
- Efficient single‑GPU deployment
- Edge‑deployable via quantized variants
Limits
- Requires large VRAM for full precision
- No explicit language support listed
- Mixture‑of‑experts may increase latency
Best for
- Vision‑centric applications on a single GPU
- Edge devices needing a lightweight variant
- Research on MOE architectures
Who it’s for. Developers and researchers looking for a large vision‑capable model that can run on a single GPU or be further quantized for mobile use. The MIT license allows free modification and redistribution.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 75.8 GB | 77.2 GB | Too big | Get file → | |
| Q5_K_M | 88.7 GB | 90.0 GB | Too big | Get file → | |
| Q6_K | 102.4 GB | 103.7 GB | Too big | Get file → | |
| Q8_0 | 132.6 GB | 133.9 GB | Too big | Get file → | |
| BF16 | 249.4 GB | 250.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (75.84 GB file, ~77 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (88.71 GB file, ~90 GB memory). For 16 GB VRAM, Q6_K (102.38 GB file, ~103.7 GB memory). Higher precision quants require more 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: no quant fits at an 8K context.
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 75.8 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.
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 77.2 GB at Q4_K_M with an 8K context window. That is the 75.8 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 77.2 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: Q4_K_M is 75.8 GB, Q5_K_M is 88.7 GB, Q6_K is 102.4 GB, Q8_0 is 132.6 GB, BF16 is 249.4 GB.
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 ornith-ai/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?
Only with the Q4_K_M quant, which uses about 77 GB of VRAM at 8k context – not feasible on 8 GB. You would need a higher‑quantized model or a smaller context.
Does this model support text generation?
Yes, it can generate text, but its primary design is for vision tasks and efficient single‑GPU inference.
Is the model licensed for commercial use?
It is released under the MIT license, which permits commercial use and modification.