OR

Ornith 1.5 9B Abliterated ROCmFP4

OrnithGGUF by kingjones777Updated 2026-08-30
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant5.1 GB
Quick answer

Ornith 1.5 9B Abliterated ROCmFP4 needs about 7.1 GB of memory at Q4_0 (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 5.1 GB (Q4_0) to 9.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Ornith 1.5 9B Abliterated ROCmFP4 – 9B dense model with vision and tools

Ornith 1.5 9B Abliterated ROCmFP4 is a 9B parameter dense model based on the qwen35 architecture. It supports reasoning, tools, and vision. The model is released under the MIT license and is intended for research and legitimate local use.

Good at

  • Reasoning
  • Tools usage
  • Vision tasks

Limits

  • No native MTP support
  • Large VRAM required for higher quant levels
  • No official release date

Best for

  • Local inference on AMD GPUs
  • Research on refusal behavior
  • Vision‑enabled text generation

Who it’s for. Developers and researchers who need a 9B dense model with vision and tool capabilities. The model is suitable for local deployment on systems with AMD GPUs that support ROCmFP4 quantisation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_05.1 GB 6.6 GB
Fits Get file →
Q4_05.3 GB 6.8 GB
Fits Get file →
Q4_05.6 GB 7.1 GB
Fits Get file →
Q6_08.5 GB 10.0 GB
Too big Get file →
Q8_09.3 GB 10.9 GB
Too big Get file →
Q8_09.4 GB 11.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (5.07 GB) or Q4_0 (5.25 GB) files; memory usage is approximately 6.6 GB or 6.8 GB at 8 k context. For 12 GB VRAM, Q6_0 (8.46 GB) or Q8_0 (9.28 GB) are viable, with memory estimates around 10 GB or 10.9 GB. Choose the smallest file that fits your VRAM budget.

What GPU do you need for Ornith 1.5 9B 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: the best quant that fits is Q4_0 (5.6 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.4 GB file, about 11.0 GB in use).

Which Ornith 1.5 9B Abliterated ROCmFP4 quant should you choose?

Q4_0 (5.6 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 5.1 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

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bykingjones777
FamilyOrnith
Licensemit
Downloads (HF)477
Last updated2026-08-30

Frequently asked questions about Ornith 1.5 9B Abliterated ROCmFP4

How much VRAM does Ornith 1.5 9B Abliterated ROCmFP4 need?

About 7.1 GB at Q4_0 with an 8K context window. That is the 5.6 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 9B Abliterated ROCmFP4 on an 8 GB GPU?

Yes, with Q4_0: the 5.6 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ornith 1.5 9B Abliterated ROCmFP4 GGUF?

It depends on the quant: Q4_0 is 5.1 GB, Q4_0 is 5.3 GB, Q4_0 is 5.6 GB, Q6_0 is 8.5 GB, Q8_0 is 9.3 GB, Q8_0 is 9.4 GB.

What context length does Ornith 1.5 9B 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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Ornith 1.5 9B Abliterated ROCmFP4 GGUF?

The files are on Hugging Face in the kingjones777/Ornith-1.5-9B-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 9B Abliterated ROCmFP4 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 9B Abliterated ROCmFP4 on 8 GB VRAM?

Yes, the Q4_0 quantisations (5.07 GB or 5.25 GB) require about 6.6 GB or 6.8 GB of VRAM at 8 k context, which fits within 8 GB.

Does this model support vision tasks?

Yes, it includes a vision projector compatible with all text GGUF files in the repository.

What license applies to this model?

The model is released under the MIT license.

Similar models

Browse all →

More from kingjones777

All by kingjones777 →

More Ornith models

All Ornith →

Other small models

All small models →