OR

Ornith-1.5-35B-A3B-DFlash2-draft

OrnithGGUF by Cobra91310Updated 2026-09-14
Download on Hugging Face
Parameters526M
Context256K
Layers6
Architecturedflash
Smallest quant1.1 GB
Quick answer

Ornith-1.5-35B-A3B-DFlash2-draft needs about 1.8 GB of memory at F16 (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.

Ornith-1.5-35B-A3B-DFlash2 draft model for llama.cpp

A 0.5B dense drafter with 6 layers and 262144 trained context tokens. It is a GGUF conversion of jzinno's DFlash2 drafter for Ornith-1.5-35B-A3B. Requires a compatible Ornith target checkpoint and a llama.cpp build with DFlash2 support.

Good at

  • Reasoning
  • Tools integration
  • Speculative decoding

Limits

  • Not a standalone language model
  • Requires Ornith target checkpoint
  • No vision support

Best for

  • Fast inference with draft network
  • Low‑memory speculative decoding
  • Tool‑enabled LLM workflows

Who it’s for. Developers building lightweight inference pipelines that need a drafter for Ornith-1.5-35B-A3B. It is suitable for users who have a llama.cpp build with DFlash2 support and can supply the target checkpoint at runtime.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F161.1 GB 1.8 GB
Fits Get file →

The only available quant is F16, 1.06 GB file size. It requires about 1.8 GB VRAM at 8 k context. For 8 GB VRAM users, F16 is the recommended choice. No other quants are provided.

What GPU do you need for Ornith-1.5-35B-A3B-DFlash2-draft?

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 F16 (1.1 GB file, about 1.8 GB in use).

Which Ornith-1.5-35B-A3B-DFlash2-draft quant should you choose?

F16 (1.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters526M
Layers6
Trained context262,144 tokens
KV cache (fp16)24 KB per token

Source

Quantized byCobra91310
FamilyOrnith
Licenseapache-2.0
Downloads (HF)519
Last updated2026-09-14

Frequently asked questions about Ornith-1.5-35B-A3B-DFlash2-draft

How much VRAM does Ornith-1.5-35B-A3B-DFlash2-draft need?

About 1.8 GB at F16 with an 8K context window. That is the 1.1 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-DFlash2-draft on an 8 GB GPU?

Yes, with F16: the 1.1 GB file needs about 1.8 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-A3B-DFlash2-draft GGUF?

It depends on the quant: F16 is 1.1 GB.

What context length does Ornith-1.5-35B-A3B-DFlash2-draft support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.8 GB at 32K.

Where can I download Ornith-1.5-35B-A3B-DFlash2-draft GGUF?

The files are on Hugging Face in the Cobra91310/Ornith-1.5-35B-A3B-DFlash2-draft-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-DFlash2-draft 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 this model on 8 GB VRAM?

Yes, the F16 quant uses about 1.8 GB VRAM at 8 k context, leaving room for other processes.

Does it support vision tasks?

No, the model has no vision capabilities.

What license does it use?

Apache-2.0, same as the source model.

Similar models

Browse all →

More from Cobra91310

All by Cobra91310 →

More Ornith models

All Ornith →

Other tiny models

All tiny models →