OR

Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill

OrnithGGUF by xoykorUpdated 2026-09-20
Download on Hugging Face
Parameters9.2B
Context256K
Layers33
Architectureqwen35
Smallest quant6.6 GB
Quick answer

Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill needs about 8.2 GB of memory at Q5_K_M (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill – agentic tool‑use LLM

Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill is a 9.2B‑parameter dense model fine‑tuned for agentic workflows, tool use, and coding. It inherits multimodal vision from the base Ornith model and is released under an MIT license.

Good at

  • Agentic tool use
  • Coding tasks
  • Multimodal vision

Limits

  • No vision support beyond F16 mmproj projector
  • Requires 8.2 GB RAM at 8 k context
  • No GPU acceleration specified

Best for

  • Local agent harnesses
  • Tool‑heavy development workflows
  • DSH / DeepSeek harnesses

Who it’s for. Developers building local agents that need quick tool interactions and coding assistance. The model is suitable for single‑GPU or edge deployments where a lightweight 9B model is desired.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M6.6 GB 8.2 GB
Too big Get file →

The Q5_K_M quantization is 6.64 GB on disk and needs about 8.2 GB of RAM for an 8 k context window. For 4 k context the memory requirement is slightly lower. If your system has less than 8 GB RAM, consider a lower‑precision quantization not listed here.

What GPU do you need for Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill?

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: the best quant that fits is Q5_K_M (6.6 GB file, about 8.2 GB in use).

Which Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill quant should you choose?

Q5_K_M (6.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters9.2B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized byxoykor
FamilyOrnith
Licensemit
Downloads (HF)897
Last updated2026-09-20

Frequently asked questions about Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill

How much VRAM does Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill need?

About 8.2 GB at Q5_K_M with an 8K context window. That is the 6.6 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 DSH Agentic GPT 5.6 Sol Distill on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill GGUF?

It depends on the quant: Q5_K_M is 6.6 GB.

What context length does Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill 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 4.4 GB at 32K.

Where can I download Ornith 1.5 9B DSH Agentic GPT 5.6 Sol Distill GGUF?

The files are on Hugging Face in the xoykor/Ornith-1.5-9B-DSH-Agentic-GPT-5.6-Sol-Distill 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 DSH Agentic GPT 5.6 Sol Distill 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 this model on 8 GB VRAM?

The model requires 8.2 GB of RAM for an 8 k context, so 8 GB VRAM is insufficient for full inference.

Is the model compatible with OpenAI‑style agent harnesses?

Yes, it is designed for OpenAI‑compatible agent harnesses and DSH workflows.

Does the model support vision?

It includes an F16 mmproj vision projector, enabling multimodal input.

Other GGUFs of Ornith-1.5-9B

Similar models

Browse all →

More Ornith models

All Ornith →

Other small models

All small models →