Ornith 1.5 35B A3B Heretic MTP APEX needs about 18.5 GB of memory at its main file (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 14.3 GB to 26.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Ornith 1.5 35B A3B Heretic MTP APEX – a multimodal Qwen3.5 MoE model
Ornith 1.5 35B A3B Heretic MTP APEX is a 35B parameter mixture‑of‑experts model based on Qwen3.5 MoE. It activates 3B parameters per token and supports vision and text. The model is released under the MIT license and is available as GGUF files.
Good at
- Reasoning and problem solving
- Vision‑enabled multimodal tasks
- Agentic coding and tool use
Limits
- Requires large VRAM for full 8‑k context
- No pre‑trained MTP head – may need fine‑tuning
- Only text and vision, no audio
Best for
- Developers building multimodal agents
- Researchers testing MoE architectures
- Users needing large context for coding
Who it’s for. The model is suited for developers and researchers who need a large‑context, multimodal LLM with mixture‑of‑experts efficiency. It is ideal for building agents that combine vision and text reasoning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.3 GB | 15.5 GB | Too big | Get file → | |
| — | 17.3 GB | 18.5 GB | Too big | Get file → | |
| — | 23.5 GB | 24.7 GB | Too big | Get file → | |
| — | 26.1 GB | 27.2 GB | Too big | Get file → |
For 8‑k context, the 14.27 GB file needs about 15.5 GB VRAM. If you have 16 GB VRAM, use the 14.27 GB file. With 24 GB VRAM, the 23.49 GB file is suitable. For 32 GB VRAM, the 26.06 GB file provides the highest performance.
What GPU do you need for Ornith 1.5 35B A3B Heretic MTP APEX?
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 (14.3 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (17.3 GB file, about 18.5 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (26.1 GB file, about 27.2 GB in use).
Which Ornith 1.5 35B A3B Heretic MTP APEX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 14.3 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 A3B Heretic MTP APEX
How much VRAM does Ornith 1.5 35B A3B Heretic MTP APEX need?
About 18.5 GB at its main file with an 8K context window. That is the 17.3 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 A3B Heretic MTP APEX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.5 35B A3B Heretic MTP APEX GGUF?
It depends on the quant: file is 14.3 GB, file is 17.3 GB, file is 23.5 GB, file is 26.1 GB.
What context length does Ornith 1.5 35B A3B Heretic MTP APEX 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 A3B Heretic MTP APEX GGUF?
The files are on Hugging Face in the SC117/Ornith-1.5-35B-A3B-Heretic-MTP-APEX-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 A3B Heretic MTP APEX 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 smallest 8‑k context memory estimate is 15.5 GB, which exceeds 8 GB VRAM.
Does the model support vision?
Yes, the model includes vision capability as indicated by the detected abilities.
What license applies to this model?
The model is released under the MIT license.