Ornith 1.5 9B DFlash needs about 1.5 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.8 GB (Q4_K_M) to 2.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.
Ornith 1.5 9B DFlash – speculative decoding draft for Ornith-1.5-9B
Ornith 1.5 9B DFlash is a speculative decoding draft model based on the dflash architecture. It is designed to accelerate inference of Ornith-1.5-9B by drafting up to 16 tokens per step. The model is distributed in GGUF format and licensed under MIT.
Good at
- Speculative decoding
- Drafting 16 tokens per step
- Compatible with Ornith-1.5-9B
Limits
- Requires Ornith-1.5-9B as target
- Not a standalone LLM
- No vision support
Best for
- Speeding up Ornith-1.5-9B inference
- Low‑latency generation on single GPU
- Edge deployment with draft model
Who it’s for. Developers and researchers who run Ornith-1.5-9B on llama.cpp and need higher throughput. The draft model works only when paired with the base Ornith-1.5-9B GGUF.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 1.4 GB | 2.1 GB | Fits | Get file → | |
| BF16 | 2.6 GB | 3.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.77 GB, ~1.5 GB RAM). For 12 GB VRAM, Q6_K (1.07 GB, ~1.8 GB RAM) is suitable. Higher precision quants increase memory usage and are not recommended for limited VRAM.
What GPU do you need for Ornith 1.5 9B 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 (2.6 GB file, about 3.3 GB in use).
Which Ornith 1.5 9B DFlash quant should you choose?
Q4_K_M is the usual starting point for Ornith 1.5 9B DFlash: it balances file size and quality well. Here it is a 0.8 GB file.
The Q8_0 file is 1.4 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornith 1.5 9B DFlash
How much VRAM does Ornith 1.5 9B DFlash need?
About 1.5 GB at Q4_K_M with an 8K context window. That is the 0.8 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 DFlash on an 8 GB GPU?
Yes, with BF16: the 2.6 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ornith 1.5 9B DFlash GGUF?
It depends on the quant: Q4_K_M is 0.8 GB, Q6_K is 1.1 GB, Q8_0 is 1.4 GB, BF16 is 2.6 GB.
What context length does Ornith 1.5 9B 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 9B DFlash GGUF?
The files are on Hugging Face in the abenzerps/Ornith-1.5-9B-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 9B 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 9B DFlash on 8 GB VRAM?
Yes, pair it with Ornith-1.5-9B and use the Q4_K_M quant; it requires about 1.5 GB RAM at 8 k context.
Does this model support vision tasks?
No, Ornith 1.5 9B DFlash is a text‑only draft model.
What license applies to this model?
The model is distributed under the MIT License, matching the upstream Ornith-1.5-9B-DFlash.