Ornith 1.5 35B Uncensored YMQ MTP needs about 14.6 GB of memory at its main file (a 13.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 12.0 GB to 18.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Ornith 1.5 35B Uncensored YMQ MTP – a large MoE model with vision and 262K context
Ornith 1.5 35B Uncensored YMQ MTP is a 35.5B parameter model built on the qwen35moe architecture. It retains native vision support and a 262,144 token context window. The model is released under the apache-2.0 license.
Good at
- Vision tasks with high context
- Large‑scale multi‑token prediction
- Agentic coding and self‑improvement
Limits
- Requires recent runtimes such as Transformers 5.8.1+ or vLLM 0.19.1+
- No explicit GPU memory limits listed
- No non‑vision modalities beyond vision
Best for
- Vision‑enabled local agents
- Long‑form content generation with 262K context
- Complex coding assistance
Who it’s for. Developers and researchers needing a large MoE model with vision and extended context for local deployment. The model is suitable for advanced agent systems and coding assistants that require uncensored behavior and high token limits.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 12.0 GB | 13.2 GB | Too big | Get file → | |
| — | 13.4 GB | 14.6 GB | Too big | Get file → | |
| — | 16.2 GB | 17.4 GB | Too big | Get file → | |
| — | 18.6 GB | 19.8 GB | Too big | Get file → |
The model ships in four quantizations. For 8 GB VRAM use the 11.97 GB file (est. 13.2 GB memory at 8 k context). For 12 GB VRAM use the 13.42 GB file (est. 14.6 GB). For 16 GB VRAM use the 16.18 GB file (est. 17.4 GB). For 20 GB VRAM use the 18.64 GB file (est. 19.8 GB).
What GPU do you need for Ornith 1.5 35B Uncensored YMQ MTP?
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: the best quant that fits is the main file (13.4 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (18.6 GB file, about 19.8 GB in use).
Which Ornith 1.5 35B Uncensored YMQ MTP quant should you choose?
If memory is tight, the smallest file is the first one in the table at 12.0 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 35B Uncensored YMQ MTP
How much VRAM does Ornith 1.5 35B Uncensored YMQ MTP need?
About 14.6 GB at its main file with an 8K context window. That is the 13.4 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 35B Uncensored YMQ MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.5 35B Uncensored YMQ MTP GGUF?
It depends on the quant: file is 12.0 GB, file is 13.4 GB, file is 16.2 GB, file is 18.6 GB.
What context length does Ornith 1.5 35B Uncensored YMQ MTP 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 2.8 GB at 32K.
Where can I download Ornith 1.5 35B Uncensored YMQ MTP GGUF?
The files are on Hugging Face in the zerodigest/Ornith-1.5-35B-Uncensored-YMQ-MTP-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 35B Uncensored YMQ MTP use?
Hugging Face lists the license as apache-2.0. 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 35B on 8 GB VRAM?
The 11.97 GB quantization requires about 13.2 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does this model support vision?
Yes, the model includes native vision support as detected by the card.
What license applies to this model?
The model is released under the apache-2.0 license.