sendai and miyagi needs about 4.9 GB of memory at Q8_0 (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.4 GB (Q8_0) to 3.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
sendai and miyagi is a 3.21B-parameter Llama model in GGUF format, quantized by Ken1drick. Its trained context length is 128K tokens. The repository has 2 quant files, from 3.4 GB (Q8_0) to 3.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 3.4 GB | 4.9 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.9 GB | Fits | Get file → |
What GPU do you need for sendai and miyagi?
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: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
Which sendai and miyagi quant should you choose?
Q8_0 (3.4 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
Source
Frequently asked questions about sendai and miyagi
How much VRAM does sendai and miyagi need?
About 4.9 GB at Q8_0 with an 8K context window. That is the 3.4 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 sendai and miyagi on an 8 GB GPU?
Yes, with Q8_0: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of sendai and miyagi GGUF?
It depends on the quant: Q8_0 is 3.4 GB, Q8_0 is 3.4 GB.
What context length does sendai and miyagi support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download sendai and miyagi GGUF?
The files are on Hugging Face in the Ken1drick/sendai_and_miyagi repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.