OR

Ornith-1.5-35B

OrnithGGUF by na0x2c6Updated 2026-10-23
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant0.4 GB
Quick answer

Ornith-1.5-35B needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 0.4 GB to 22.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Ornith-1.5-35B-A3B: a 35.5B mixture‑of‑experts LLM

Ornith-1.5-35B-A3B is a 35.5B parameter model that activates ~3B parameters per token. It is trained on 262144 context tokens and released under the MIT license. The model is part of the Ornith family and uses the qwen35moe architecture.

Good at

  • High‑capacity coding tasks
  • Agentic reasoning
  • Long‑context generation

Limits

  • Requires large VRAM for full‑precision use
  • No vision support in the base GGUF
  • Limited to 8‑k context for memory estimates

Best for

  • Developers building coding assistants
  • Researchers testing mixture‑of‑experts performance
  • Teams needing a large‑context LLM

Who it’s for. This model suits developers and researchers who need a large‑parameter LLM with a mixture‑of‑experts design. It is ideal for those who can allocate sufficient VRAM and are working within the MIT license constraints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 1.6 GB
Fits Get file →
IQ2_XS13.2 GB 14.4 GB
Too big Get file →
IQ2_S14.4 GB 15.5 GB
Too big Get file →
IQ3_XXS15.7 GB 16.9 GB
Too big Get file →
IQ3_S16.1 GB 17.2 GB
Too big Get file →
IQ3_S16.7 GB 17.9 GB
Too big Get file →
IQ3_S17.5 GB 18.7 GB
Too big Get file →
IQ3_S18.1 GB 19.3 GB
Too big Get file →
IQ4_XS19.3 GB 20.5 GB
Too big Get file →
IQ4_XS20.0 GB 21.2 GB
Too big Get file →
Q4_K_M21.7 GB 22.9 GB
Too big Get file →
Q4_K_M22.4 GB 23.6 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_XS (13.18 GB file, 14.4 GB memory at 8k context). For 16‑GB VRAM, IQ4_XS (19.32 GB file, 20.5 GB memory) or Q4_K_M (21.71 GB file, 22.9 GB memory) are suitable. Larger VRAM allows the full‑precision file (0.38 GB).

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

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: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_S (14.4 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (22.4 GB file, about 23.6 GB in use).

Which Ornith-1.5-35B quant should you choose?

Q4_K_M is the usual starting point for Ornith-1.5-35B: it balances file size and quality well. Here it is a 21.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.4 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

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

Source

Quantized byna0x2c6
FamilyOrnith
Licensemit
Downloads (HF)5,807
Last updated2026-10-23

Frequently asked questions about Ornith-1.5-35B

How much VRAM does Ornith-1.5-35B need?

About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 on an 8 GB GPU?

Yes, with the smaller files: the 0.4 GB file needs about 1.6 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 GGUF?

It depends on the quant: file is 0.4 GB, IQ2_XS is 13.2 GB, IQ2_S is 14.4 GB, IQ3_XXS is 15.7 GB, IQ3_S is 16.1 GB, IQ3_S is 16.7 GB and 6 more.

What context length does Ornith-1.5-35B 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 GGUF?

The files are on Hugging Face in the na0x2c6/Ornith-1.5-35B-A3B-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 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?

Use the IQ2_XS quantized file; it requires 13.18 GB file size and estimates 14.4 GB VRAM at 8k context.

Does the model support image input?

The base GGUF does not include vision; use the separate vision projector from the official repo for image input.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of Ornith-1.5-35B-A3B

Similar models

Browse all →

More from na0x2c6

All by na0x2c6 →

More Ornith models

All Ornith →

Other large models

All large models →