Ornith 1.5 35B A3B APEX MTP needs about 24.9 GB of memory at its main file (a 23.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 7 quants, from 14.4 GB to 26.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Ornith 1.5 35B A3B APEX MTP – a 36 B parameter Mixture‑of‑Experts model with vision support
Ornith 1.5 35B A3B APEX MTP is a 36 B parameter Mixture‑of‑Experts model built on qwen35moe architecture. It includes a vision tower and a next‑N draft head (MTP). The model activates ~3 B parameters per token and supports a 262 144‑token context.
Good at
- Large‑context reasoning
- Vision‑enabled tasks
- Mixture‑of‑Experts efficiency
Limits
- Requires high VRAM for full‑precision run
- No text‑only quant available
- License is Apache‑2.0
Best for
- Complex coding with vision prompts
- Agentic workflows needing large context
- Research on MoE architectures
Who it’s for. Developers and researchers needing a large‑context, vision‑enabled LLM with Mixture‑of‑Experts architecture. The model is suitable for advanced coding, agentic tasks, and vision‑based inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.4 GB | 15.6 GB | Too big | Get file → | |
| — | 17.4 GB | 18.6 GB | Too big | Get file → | |
| — | 17.4 GB | 18.6 GB | Too big | Get file → | |
| — | 23.7 GB | 24.9 GB | Too big | Get file → | |
| — | 23.7 GB | 24.9 GB | Too big | Get file → | |
| — | 26.2 GB | 27.4 GB | Too big | Get file → | |
| — | 26.2 GB | 27.4 GB | Too big | Get file → |
For 8 GB VRAM, use the 14.37 GB file (est. 15.6 GB memory at 8 k context). For 16 GB VRAM, the 17.44 GB file (est. 18.6 GB memory) is appropriate. Larger VRAM allows the 23.72 GB or 26.17 GB files with higher memory estimates.
What GPU do you need for Ornith 1.5 35B A3B APEX 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 (14.4 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (17.4 GB file, about 18.6 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (26.2 GB file, about 27.4 GB in use).
Which Ornith 1.5 35B A3B APEX MTP quant should you choose?
If memory is tight, the smallest file is the first one in the table at 14.4 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 APEX MTP
How much VRAM does Ornith 1.5 35B A3B APEX MTP need?
About 24.9 GB at its main file with an 8K context window. That is the 23.7 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 APEX MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.5 35B A3B APEX MTP GGUF?
It depends on the quant: file is 14.4 GB, file is 17.4 GB, file is 17.4 GB, file is 23.7 GB, file is 23.7 GB, file is 26.2 GB and 1 more.
What context length does Ornith 1.5 35B A3B APEX 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 A3B APEX MTP GGUF?
The files are on Hugging Face in the mudler/Ornith-1.5-35B-A3B-APEX-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 A3B APEX 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 A3B on 8 GB VRAM?
The 14.37 GB file estimates 15.6 GB memory at 8 k context, so 8 GB VRAM is insufficient for full‑precision inference.
Does this model support vision tasks?
Yes, the model includes a vision tower and is detected to have vision abilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.