Ornith 1.5 Reap50 12Gcard mixQuant needs about 9.1 GB of memory at its main file (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Ornith 1.5 Reap50 12Gcard mixQuant – a 18.5B MoE model optimized for 12 GB cards
Ornith 1.5 Reap50 12Gcard mixQuant is a mixture‑of‑experts model based on Ornith‑1.5‑35B‑A3B. It uses a 262144‑token context and is quantized by TSalpha. The model is released under the MIT license and supports reasoning and tools.
Good at
- Reasoning
- Tool use
- Large context
Limits
- Requires ~9.1 GB VRAM at 8 k context
- Mixture‑of‑experts architecture
- No vision support
Best for
- LLM inference on 12 GB GPUs
- Research on MoE models
- Applications needing long context
Who it’s for. Researchers and developers who need a large‑parameter MoE model that can run on 12 GB GPUs. The model is suitable for tasks that benefit from long‑context reasoning and tool integration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 7.9 GB | 9.1 GB | Too big | Get file → |
The available GGUF file is 7.94 GB and requires approximately 9.1 GB of VRAM at 8 k context. For 12 GB VRAM this quantization is suitable. If you have less VRAM, a different quantization would be needed, but none is listed.
What GPU do you need for Ornith 1.5 Reap50 12Gcard mixQuant?
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: the best quant that fits is the main file (7.9 GB file, about 9.1 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornith 1.5 Reap50 12Gcard mixQuant
How much VRAM does Ornith 1.5 Reap50 12Gcard mixQuant need?
About 9.1 GB at its main file with an 8K context window. That is the 7.9 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 Reap50 12Gcard mixQuant on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.5 Reap50 12Gcard mixQuant GGUF?
It depends on the quant: file is 7.9 GB.
What context length does Ornith 1.5 Reap50 12Gcard mixQuant support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Ornith 1.5 Reap50 12Gcard mixQuant GGUF?
The files are on Hugging Face in the TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant 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 Reap50 12Gcard mixQuant 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 this model on 8 GB VRAM?
No. The model requires about 9.1 GB of VRAM at 8 k context, so 8 GB is insufficient.
What license does this model use?
The model is released under the MIT license.
Is this a mixture‑of‑experts model?
Yes, it activates only ~3 B parameters per token and is a MoE architecture.