Ornith 1.0 35B Heretic MTP APEX needs about 19.9 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 6 quants, from 0.2 GB to 71.1 GB (BF16).
Ornith 1.0 35B Heretic MTP APEX – a multimodal coding model
Ornith 1.0 35B Heretic MTP APEX is a 35B parameter model based on Qwen3.5 MoE. It merges a Heretic 1.4.0 LoRA into BF16 weights and includes a Qwen3.5 MTP head and BF16 vision projector. The model is released under the MIT license.
Good at
- Multimodal reasoning
- Coding assistance
- Vision + text integration
Limits
- Large context of 262,144 tokens
- Requires 8,000 token context for memory estimates
- No explicit vision-only support beyond the projector
Best for
- Agentic coding tasks
- Multimodal prompt engineering
- MTP speculative decoding
Who it’s for. Developers and researchers who need a multimodal model with coding and vision capabilities. The model is suitable for experimentation with MTP acceleration and APEX quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| — | 14.3 GB | 16.5 GB | Too big | Get file → | |
| — | 17.3 GB | 19.9 GB | Too big | Get file → | |
| — | 23.5 GB | 26.8 GB | Too big | Get file → | |
| — | 26.1 GB | 29.8 GB | Too big | Get file → | |
| BF16 | 71.1 GB | 80.1 GB | Too big | Get file → |
For 8 GB VRAM, use the *-APEX-I-Mini.gguf (13.29 GiB) or *-APEX-I-Compact.gguf (16.14 GiB). For 16 GB VRAM, *-APEX-I-Balanced.gguf (24.33 GiB) or *-APEX-I-Quality.gguf (21.87 GiB) are appropriate. Memory estimates are approximate.
What GPU do you need for Ornith 1.0 35B Heretic MTP APEX?
These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.2 GB file, about 0.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (17.3 GB file, about 19.9 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (26.1 GB file, about 29.8 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (26.1 GB file, about 29.8 GB in use).
Which Ornith 1.0 35B Heretic MTP APEX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.2 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 1.0 35B Heretic MTP APEX
How much VRAM does Ornith 1.0 35B Heretic MTP APEX need?
About 19.9 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 1.0 35B Heretic MTP APEX on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ornith 1.0 35B Heretic MTP APEX GGUF?
It depends on the quant: file is 0.2 GB, file is 14.3 GB, file is 17.3 GB, file is 23.5 GB, file is 26.1 GB, BF16 is 71.1 GB.
Where can I download Ornith 1.0 35B Heretic MTP APEX GGUF?
The files are on Hugging Face in the SC117/Ornith-1.0-35B-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 1.0 35B 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 Ornith 1.0 35B on 8 GB VRAM?
Use the *-APEX-I-Mini.gguf or *-APEX-I-Compact.gguf variants. They fit within 8 GB VRAM with the recommended settings.
Does the model support vision tasks?
Yes, it includes a BF16 vision projector for multimodal inputs.
What is the recommended context length?
The model supports up to 262,144 tokens, but memory estimates are for 8,000 token context.