OR

Ornith 1.5 35B A3B DFlash

OrnithGGUF by na0x2c6Updated 2026-10-01
Download on Hugging Face
Parameters386M
Context256K
Layers6
Architecturedflash
Smallest quant0.4 GB
Quick answer

Ornith 1.5 35B A3B DFlash needs about 1.1 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q8_0) to 0.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.

Ornith 1.5 35B A3B DFlash – a draft‑accelerated reasoning model

Ornith 1.5 35B A3B DFlash pairs the Ornith‑1.5‑35B‑A3B target model with a DFlash draft model for speculative decoding. The draft model proposes token blocks while the target verifies them, improving throughput. The model is 0.386 billion parameters and supports a 262144‑token context.

Good at

  • Speculative decoding acceleration
  • Reasoning with chain‑of‑thought output
  • Large context handling

Limits

  • No vision support
  • Requires DFlash‑enabled inference stack
  • License is MIT

Best for

  • Speed‑critical inference on GPUs
  • Research on speculative decoding
  • Large‑context reasoning tasks

Who it’s for. Developers and researchers who need a reasoning model with speculative decoding acceleration. The model works best when paired with a compatible Ornith‑1.5‑35B‑A3B GGUF and a recent llama.cpp build.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.4 GB 1.1 GB
Fits Get file →
BF160.8 GB 1.5 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (0.42 GB file, ~1.1 GB RAM at 8 k context). For 16 GB VRAM, BF16 (0.78 GB file, ~1.5 GB RAM at 8 k context) offers a higher‑quality option. Memory estimates are approximate.

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

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 BF16 (0.8 GB file, about 1.5 GB in use).

Which Ornith 1.5 35B A3B DFlash quant should you choose?

Q8_0 (0.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters386M
Layers6
Trained context262,144 tokens
KV cache (fp16)24 KB per token

Source

Quantized byna0x2c6
FamilyOrnith
Licensemit
Downloads (HF)3,341
Last updated2026-10-01

Frequently asked questions about Ornith 1.5 35B A3B DFlash

How much VRAM does Ornith 1.5 35B A3B DFlash need?

About 1.1 GB at Q8_0 with an 8K context window. That is the 0.4 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 DFlash on an 8 GB GPU?

Yes, with BF16: the 0.8 GB file needs about 1.5 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 DFlash GGUF?

It depends on the quant: Q8_0 is 0.4 GB, BF16 is 0.8 GB.

What context length does Ornith 1.5 35B A3B DFlash 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 DFlash GGUF?

The files are on Hugging Face in the na0x2c6/Ornith-1.5-35B-A3B-DFlash-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 DFlash 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 DFlash on 8 GB VRAM?

Yes, the Q8_0 quant requires about 1.1 GB RAM at 8 k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license does it use?

MIT, same as the original Ornith‑1.5‑35B‑A3B model.

Similar models

Browse all →

More from na0x2c6

All by na0x2c6 →

More Ornith models

All Ornith →

Other tiny models

All tiny models →