Ornith 1.5 35B A3B MXFP4 MOE Hybrid Imatrix needs about 21.2 GB of memory at MXFP4_MOE (a 18.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 0.2 GB to 20.7 GB (MXFP4_MOE).
Ornith 1.5 35B A3B MXFP4 MOE Hybrid Imatrix – a 35B mixture‑of‑experts model with custom mixed‑precision GGUFs
Ornith 1.5 35B A3B is a 35‑billion‑parameter mixture‑of‑experts model that activates about 3 B parameters per token. It is quantized with MXFP4 MOE and includes an Imatrix for improved instruction following and reasoning. The model is released under the MIT license.
Good at
- Tool‑enabled reasoning
- Agentic coding
- Instruction following
Limits
- No vision support
- Requires large VRAM for full precision
- No explicit language support list
Best for
- Agentic coding tasks
- Tool‑based workflows
- Instruction‑driven code generation
Who it’s for. Developers and researchers who need a large, tool‑aware model for coding and agentic tasks. The model is suitable for users with access to GPUs that can handle the VRAM demands of the MXFP4 MOE quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| MXFP4_MOE | 18.5 GB | 21.2 GB | Too big | Get file → | |
| MXFP4_MOE | 19.8 GB | 22.7 GB | Too big | Get file → | |
| MXFP4_MOE | 20.7 GB | 23.7 GB | Too big | Get file → |
For 8 GB VRAM, use the 0.19 GB quant (unknown). For 16 GB VRAM, the 18.5 GB quant (MXFP4_MOE) is suitable, estimating 21.2 GB memory at 8 k context. For 24 GB VRAM, the 19.79 GB quant (MXFP4_MOE) uses about 22.7 GB memory. For 32 GB VRAM, the 20.75 GB quant (MXFP4_MOE) uses about 23.7 GB memory. These estimates are approximate.
What GPU do you need for Ornith 1.5 35B A3B MXFP4 MOE Hybrid Imatrix?
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 MXFP4_MOE (20.7 GB file, about 23.7 GB in use).
Which Ornith 1.5 35B A3B MXFP4 MOE Hybrid Imatrix quant should you choose?
MXFP4_MOE (18.5 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
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 1.5 35B A3B MXFP4 MOE Hybrid Imatrix
How much VRAM does Ornith 1.5 35B A3B MXFP4 MOE Hybrid Imatrix need?
About 21.2 GB at MXFP4_MOE with an 8K context window. That is the 18.5 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 MOE Hybrid Imatrix 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 1.5 35B A3B MXFP4 MOE Hybrid Imatrix GGUF?
It depends on the quant: file is 0.2 GB, MXFP4_MOE is 18.5 GB, MXFP4_MOE is 19.8 GB, MXFP4_MOE is 20.7 GB.
Where can I download Ornith 1.5 35B A3B MXFP4 MOE Hybrid Imatrix GGUF?
The files are on Hugging Face in the jashepp/Ornith-1.5-35B-A3B-MXFP4_MOE_Hybrid-Imatrix-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 MOE Hybrid Imatrix 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 1.5 35B A3B on 8 GB VRAM?
Only the 0.19 GB quant is small enough for 8 GB VRAM, but it is an unknown quant and may not support all features.
Does this model support vision?
No, the model does not have vision capabilities.
What license does Ornith 1.5 35B A3B use?
The model is released under the MIT license.