SH

shisa v2.1 unphi4 14b i1

ShisaGGUF by mradermacherUpdated 2025-12-10
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturellama
Smallest quant0.0 GB
Quick answer

shisa v2.1 unphi4 14b i1 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 25 quants, from 0.0 GB to 12.0 GB (Q6_K).

Shisa V2.1 14B Japanese‑English chat model in GGUF format

Shisa V2.1 14B is a bilingual Japanese and English chat model. It is based on the llama architecture and trained on a 14.7B parameter set. The model supports a 16384 token context window.

Good at

  • Japanese language tasks
  • English chat
  • Instruction following

Limits

  • No vision support
  • Requires 8K context for memory estimates
  • MIT license only

Best for

  • Local Japanese‑English chat
  • Translation assistance
  • Edge‑device inference

Who it’s for. Developers and researchers needing a bilingual Japanese‑English model for local inference. The model is suitable for applications that can run llama.cpp with a 14.7B parameter size.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.2 GB
Fits Get file →
IQ1_S3.4 GB 5.6 GB
Fits Get file →
IQ1_M3.7 GB 5.9 GB
Fits Get file →
IQ2_XXS4.2 GB 6.3 GB
Fits Get file →
IQ2_XS4.6 GB 6.7 GB
Fits Get file →
IQ2_S4.8 GB 7.0 GB
Fits Get file →
IQ2_M5.2 GB 7.4 GB
Tight Get file →
Q2_K_S5.2 GB 7.4 GB
Tight Get file →
Q2_K5.6 GB 7.8 GB
Tight Get file →
IQ3_XXS5.8 GB 8.0 GB
Tight Get file →
IQ3_XS6.2 GB 8.4 GB
Too big Get file →
Q3_K_S6.5 GB 8.7 GB
Too big Get file →
IQ3_S6.5 GB 8.7 GB
Too big Get file →
IQ3_M6.7 GB 8.9 GB
Too big Get file →
Q3_K_M7.2 GB 9.4 GB
Too big Get file →
Q3_K_L7.8 GB 10.0 GB
Too big Get file →
IQ4_XS8.0 GB 10.2 GB
Too big Get file →
Q4_08.4 GB 10.6 GB
Too big Get file →
IQ4_NL8.4 GB 10.6 GB
Too big Get file →
Q4_K_S8.4 GB 10.6 GB
Too big Get file →
Q4_K_M8.9 GB 11.1 GB
Too big Get file →
Q4_19.3 GB 11.4 GB
Too big Get file →
Q5_K_S10.2 GB 12.3 GB
Too big Get file →
Q5_K_M10.4 GB 12.6 GB
Too big Get file →
Q6_K12.0 GB 14.2 GB
Too big Get file →

For 8GB VRAM, use IQ1_S (3.41 GB, 5.6 GB memory) or IQ1_M (3.69 GB, 5.9 GB memory). For 12GB VRAM, Q4_K_M (8.89 GB, 11.1 GB memory) is a good balance. Larger VRAM allows Q5_K_M or Q6_K for higher quality.

What GPU do you need for shisa v2.1 unphi4 14b i1?

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 the main file (0.0 GB file, about 2.2 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ1_M (3.7 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (5.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.3 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 14.2 GB in use).

Which shisa v2.1 unphi4 14b i1 quant should you choose?

Q4_K_M is the usual starting point for shisa v2.1 unphi4 14b i1: it balances file size and quality well. Here it is a 8.9 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters14.7B
Layers40
Trained context16,384 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymradermacher
FamilyShisa
Licensemit
Downloads (HF)488
Last updated2025-12-10

Frequently asked questions about shisa v2.1 unphi4 14b i1

How much VRAM does shisa v2.1 unphi4 14b i1 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 i1 on an 8 GB GPU?

Yes, with IQ3_XXS: the 5.8 GB file needs about 8.0 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 i1 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.4 GB, IQ1_M is 3.7 GB, IQ2_XXS is 4.2 GB, IQ2_XS is 4.6 GB, IQ2_S is 4.8 GB and 19 more.

What context length does shisa v2.1 unphi4 14b i1 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 i1 GGUF?

The files are on Hugging Face in the mradermacher/shisa-v2.1-unphi4-14b-i1-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 i1 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 IQ1_S or IQ1_M quantized files; they fit within 8 GB VRAM and use about 5.6–5.9 GB memory at 8K context.

Does this model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of shisa-v2.1-unphi4-14b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Shisa models

All Shisa →

Other medium models

All medium models →