Ornith 1.5 35B A3B Abliterated ROCmFP4 needs about 21.0 GB of memory at Q4_0 (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 18.6 GB (Q4_0) to 36.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Ornith 1.5 35B A3B Abliterated ROCmFP4 – a 34.7B MoE model with vision and reasoning
Ornith 1.5 35B A3B Abliterated ROCmFP4 is a 34.7B parameter model with 3B active experts. It supports reasoning, tools, and vision. The model is released under Apache‑2.0 and is intended for local research and evaluation of refusal‑direction editing.
Good at
- Reasoning
- Tools usage
- Vision inference
Limits
- Large context of 262144 tokens
- Requires significant VRAM for 8k context
- No safety guarantees due to abliteration
Best for
- Local research on refusal editing
- Vision‑enabled inference on AMD GPUs
- Testing MoE behavior
Who it’s for. Researchers and developers who need a local, large‑parameter model with vision and reasoning capabilities. The model is suitable for experimentation with AMD hardware and for evaluating the effects of abliteration on safety and performance.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 18.6 GB | 19.8 GB | Too big | Get file → | |
| Q4_0 | 18.7 GB | 19.9 GB | Too big | Get file → | |
| Q4_0 | 19.8 GB | 21.0 GB | Too big | Get file → | |
| Q6_0 | 32.3 GB | 33.5 GB | Too big | Get file → | |
| Q8_0 | 35.8 GB | 37.0 GB | Too big | Get file → | |
| Q8_0 | 36.4 GB | 37.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 18.65 GB, estimated 19.8 GB memory). For 12 GB VRAM, Q6_0 (32.28 GB, 33.5 GB memory) is suitable. For 16 GB VRAM, Q8_0 (35.84 GB, 37 GB memory) provides the highest quality.
What GPU do you need for Ornith 1.5 35B A3B Abliterated ROCmFP4?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_0 (19.8 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_0 (19.8 GB file, about 21.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.4 GB file, about 37.6 GB in use).
Which Ornith 1.5 35B A3B Abliterated ROCmFP4 quant should you choose?
Q4_0 (19.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q4_0 at 18.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Ornith 1.5 35B A3B Abliterated ROCmFP4
How much VRAM does Ornith 1.5 35B A3B Abliterated ROCmFP4 need?
About 21.0 GB at Q4_0 with an 8K context window. That is the 19.8 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 Abliterated ROCmFP4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.5 35B A3B Abliterated ROCmFP4 GGUF?
It depends on the quant: Q4_0 is 18.6 GB, Q4_0 is 18.7 GB, Q4_0 is 19.8 GB, Q6_0 is 32.3 GB, Q8_0 is 35.8 GB, Q8_0 is 36.4 GB.
What context length does Ornith 1.5 35B A3B Abliterated ROCmFP4 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 2.7 GB at 32K.
Where can I download Ornith 1.5 35B A3B Abliterated ROCmFP4 GGUF?
The files are on Hugging Face in the kingjones777/Ornith-1.5-35B-A3B-Abliterated-ROCmFP4-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 Abliterated ROCmFP4 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 Q4_0 on 8 GB VRAM?
Yes, Q4_0 requires approximately 19.8 GB memory at 8k context, which is close to 8 GB VRAM but may need swapping or a smaller context.
Does this model support vision?
Yes, the vision projector is included and passes an end‑to‑end image smoke test with Q4_K_M.
What license applies to this model?
The model is released under the Apache‑2.0 license.