Ornith 1.5 35B A3B MXFP4 needs about 0.9 GB of memory at its main file (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB to 19.8 GB (MXFP4).
Ornith 1.5 35B A3B MXFP4 – a 35B mixture‑of‑experts model
Ornith 1.5 35B A3B MXFP4 is a 35.5B parameter model with ~3B active parameters per token. It is quantized with MXFP4 and includes an F16 vision projector. The model is released under the MIT license.
Good at
- Coding tasks
- Agentic benchmarks
- Multi‑token prediction
Limits
- No vision support in the language‑only file
- Requires a 35B‑size model to run
- Large VRAM requirement for MXFP4
Best for
- Developers building coding assistants
- Researchers testing MoE models
- Users with high‑end GPUs
Who it’s for. This model is suitable for developers and researchers who need a large, mixture‑of‑experts foundation model for coding and agentic tasks. It is ideal for those with access to GPUs that can handle the memory demands of a 35B model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 0.9 GB | Fits | Get file → | |
| MXFP4 | 19.8 GB | 22.7 GB | Too big | Get file → |
The unknown quant file is 0.38 GB and needs about 0.9 GB of VRAM at 8k context. The MXFP4 quant file is 19.82 GB and needs about 22.7 GB of VRAM at 8k context. Choose the unknown quant for low‑memory setups and MXFP4 for higher‑end GPUs.
What GPU do you need for Ornith 1.5 35B A3B MXFP4?
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 (0.4 GB file, about 0.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 0.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 0.9 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 0.9 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 0.9 GB in use).
- 24 GB VRAM: the best quant that fits is MXFP4 (19.8 GB file, about 22.7 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornith 1.5 35B A3B MXFP4
How much VRAM does Ornith 1.5 35B A3B MXFP4 need?
About 0.9 GB at its main file with an 8K context window. That is the 0.4 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 A3B MXFP4 on an 8 GB GPU?
Yes, with the smaller files: the 0.4 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ornith 1.5 35B A3B MXFP4 GGUF?
It depends on the quant: file is 0.4 GB, MXFP4 is 19.8 GB.
Where can I download Ornith 1.5 35B A3B MXFP4 GGUF?
The files are on Hugging Face in the tsaipifong/Ornith-1.5-35B-A3B-MXFP4-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 MXFP4 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 the MXFP4 quantized model on 8 GB VRAM?
No. The MXFP4 quantized model requires approximately 22.7 GB of VRAM at 8k context.
Is the model licensed for commercial use?
Yes, the model is released under the MIT license.
Does the model support vision tasks?
The quantized file includes an F16 vision projector, but the language‑only file does not provide vision support.