DeepNarra-Hiraya needs about 0.7 GB of memory at TQ1_0 (a 0.0 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.
DeepNarra-Hiraya is a 29M-parameter Deepnarra model in GGUF format, quantized by DeepNarra. Its trained context length is 2048K tokens. The repository has 1 quant file, from 0.0 GB (TQ1_0) to 0.0 GB (TQ1_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 0.0 GB | 0.7 GB | Fits | Get file → |
What GPU do you need for DeepNarra-Hiraya?
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 TQ1_0 (0.0 GB file, about 0.7 GB in use).
Which DeepNarra-Hiraya quant should you choose?
TQ1_0 (0.0 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepNarra-Hiraya
How much VRAM does DeepNarra-Hiraya need?
About 0.7 GB at TQ1_0 with an 8K context window. That is the 0.0 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 DeepNarra-Hiraya on an 8 GB GPU?
Yes, with TQ1_0: the 0.0 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeepNarra-Hiraya GGUF?
It depends on the quant: TQ1_0 is 0.0 GB.
What context length does DeepNarra-Hiraya support?
The GGUF header lists a trained context length of 2,097,152 tokens (2048K). 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 DeepNarra-Hiraya GGUF?
The files are on Hugging Face in the DeepNarra/Hiraya repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.