shisa v2.1 unphi4 14b needs about 11.1 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 5.6 GB (Q2_K) to 15.6 GB (Q8_0).
Shisa V2.1 14B unphi4 – bilingual Japanese/English chat model
Shisa V2.1 14B unphi4 is a 14.7 billion‑parameter llama‑based model trained for Japanese and English. It offers strong Japanese language performance while maintaining robust English capabilities. The model supports a 16384‑token context window.
Good at
- Japanese language tasks
- English chat
- Instruction following
Limits
- No vision support
- Requires 8 k context for memory estimates
- MIT license limits commercial use
Best for
- Japanese‑English translation
- Chatbot development
- Edge‑device inference
Who it’s for. Developers building bilingual chat applications or translation tools that need strong Japanese performance on local hardware. The model is suitable for edge deployments where a 14 billion‑parameter model is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.6 GB | 7.8 GB | Tight | Get file → | |
| Q3_K_S | 6.5 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 7.2 GB | 9.4 GB | Too big | Get file → | |
| Q3_K_L | 7.8 GB | 10.0 GB | Too big | Get file → | |
| IQ4_XS | 8.1 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_S | 8.4 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_M | 8.9 GB | 11.1 GB | Too big | Get file → | |
| Q5_K_S | 10.2 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_M | 10.4 GB | 12.6 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 14.2 GB | Too big | Get file → | |
| Q8_0 | 15.6 GB | 17.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (8.44 GB file, ~10.6 GB memory). For 12 GB VRAM, Q5_K_S (10.15 GB file, ~12.3 GB memory). For 16 GB VRAM, Q6_K (12.03 GB file, ~14.2 GB memory). Estimates are approximate.
What GPU do you need for shisa v2.1 unphi4 14b?
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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q2_K (5.6 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (8.9 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.6 GB file, about 17.8 GB in use).
Which shisa v2.1 unphi4 14b quant should you choose?
Q4_K_M is the usual starting point for shisa v2.1 unphi4 14b: it balances file size and quality well. Here it is a 8.9 GB file.
The Q8_0 file is 15.6 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.
If memory is tight, the smallest file is Q2_K at 5.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about shisa v2.1 unphi4 14b
How much VRAM does shisa v2.1 unphi4 14b need?
About 11.1 GB at Q4_K_M with an 8K context window. That is the 8.9 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 shisa v2.1 unphi4 14b on an 8 GB GPU?
Yes, with Q2_K: the 5.6 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of shisa v2.1 unphi4 14b GGUF?
It depends on the quant: Q2_K is 5.6 GB, Q3_K_S is 6.5 GB, Q3_K_M is 7.2 GB, Q3_K_L is 7.8 GB, IQ4_XS is 8.1 GB, Q4_K_S is 8.4 GB and 5 more.
What context length does shisa v2.1 unphi4 14b support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.
Where can I download shisa v2.1 unphi4 14b GGUF?
The files are on Hugging Face in the mradermacher/shisa-v2.1-unphi4-14b-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 shisa v2.1 unphi4 14b 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 Shisa V2.1 14B on 8 GB VRAM?
Use the Q4_K_S quant, which requires about 10.6 GB of VRAM at 8 k context. It is the smallest quant that fits within 8 GB.
Does this model support image input?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the MIT license.