OR

Ornith 1.5 35B A3B

OrnithGGUF by ArtomYuanUpdated 2026-10-22
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant19.0 GB
Quick answer

Ornith 1.5 35B A3B needs about 30.6 GB of memory at Q6_0 (a 29.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 7 quants, from 19.0 GB (Q4_0) to 37.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Ornith 1.5 35B A3B – a 35B mixture‑of‑experts model with vision support

Ornith‑1.5‑35B‑A3B is a 35B‑parameter mixture‑of‑experts model based on the qwen35moe architecture. It activates about 3B parameters per token and supports up to 262,144 context tokens. The model includes a vision module bundled in the GGUF file.

Good at

  • High‑quality coding and agentic tasks
  • Large context handling
  • Vision‑enabled inference

Limits

  • Requires ROCmFPX‑compatible engine
  • Large VRAM needed for higher quants
  • No native support in standard llama.cpp

Best for

  • Local coding assistants
  • Agentic workflow automation
  • Vision‑based question answering

Who it’s for. Developers and researchers who need a large, mixture‑of‑experts model with vision capability and are able to run it on AMD GPUs with ROCm support. The model is suitable for local deployment where privacy and offline inference are priorities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_019.0 GB 20.1 GB
Too big Get file →
Q4_019.1 GB 20.3 GB
Too big Get file →
Q4_019.1 GB 20.3 GB
Too big Get file →
Q6_029.4 GB 30.6 GB
Too big Get file →
Q6_033.1 GB 34.3 GB
Too big Get file →
Q8_036.7 GB 37.9 GB
Too big Get file →
Q8_037.3 GB 38.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 quant (≈20 GB RAM at 8 k context). For 16 GB VRAM, Q6_0 (≈30–34 GB RAM). For 32 GB VRAM, Q8_0 (≈38–39 GB RAM). Memory estimates are approximate and depend on context length.

What GPU do you need for Ornith 1.5 35B A3B?

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 (19.1 GB file, about 20.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_0 (29.4 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.3 GB file, about 38.5 GB in use).

Which Ornith 1.5 35B A3B quant should you choose?

Q6_0 (29.4 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q4_0 at 19.0 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

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized byArtomYuan
FamilyOrnith
Licenseapache-2.0
Downloads (HF)8,443
Last updated2026-10-22

Frequently asked questions about Ornith 1.5 35B A3B

How much VRAM does Ornith 1.5 35B A3B need?

About 30.6 GB at Q6_0 with an 8K context window. That is the 29.4 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ornith 1.5 35B A3B GGUF?

It depends on the quant: Q4_0 is 19.0 GB, Q4_0 is 19.1 GB, Q4_0 is 19.1 GB, Q6_0 is 29.4 GB, Q6_0 is 33.1 GB, Q8_0 is 36.7 GB and 1 more.

What context length does Ornith 1.5 35B A3B 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 GGUF?

The files are on Hugging Face in the ArtomYuan/Ornith-1.5-35B-A3B-ROCmFPX 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 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?

No. The smallest quant requires about 20 GB of RAM at 8 k context, which exceeds 8 GB VRAM. You need a GPU with at least 16 GB VRAM for Q6_0 or 32 GB for Q8_0.

Does this model support vision?

Yes. The GGUF bundle includes a vision mmproj with CLIP and qwen3vl_merger towers.

What engine is required to load the ROCmFPX files?

You must use the strix.cpp fork tuned for ROCmFPX; standard llama.cpp cannot load these files.

Other GGUFs of Ornith-1.5-35B-A3B

Similar models

Browse all →

More from ArtomYuan

All by ArtomYuan →

More Ornith models

All Ornith →

Other large models

All large models →