SH

shisa 7b v1 i1

ShisaGGUF by mradermacherUpdated 2025-12-05
Download on Hugging Face
Parameters7.96B
Context32K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

shisa 7b v1 i1 needs about 6.4 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 6.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Shisa 7B v1 i1 – bilingual Japanese/English chat model

Shisa 7B v1 i1 is a 7.96B parameter llama-based model trained for strong Japanese and robust English performance. It uses a custom JA‑optimized tokenizer and synthetic‑data fine‑tuning. The model is released under Apache‑2.0.

Good at

  • Japanese conversation
  • English chat
  • General-purpose dialogue

Limits

  • No vision support
  • Requires 8k context
  • License is Apache‑2.0

Best for

  • Chatbots in Japanese
  • Multilingual support for JA/EN
  • Research on bilingual LLMs

Who it’s for. Developers building Japanese‑English chat applications or researchers needing a bilingual llama model. The model is suitable for both commercial and academic use under its permissive license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.1 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 3.9 GB
Fits Get file →
IQ2_XS2.6 GB 4.1 GB
Fits Get file →
IQ2_S2.7 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K_S2.9 GB 4.5 GB
Fits Get file →
Q2_K3.1 GB 4.7 GB
Fits Get file →
IQ3_XXS3.2 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.0 GB
Fits Get file →
Q3_K_S3.6 GB 5.2 GB
Fits Get file →
IQ3_S3.6 GB 5.2 GB
Fits Get file →
IQ3_M3.7 GB 5.3 GB
Fits Get file →
Q3_K_M4.0 GB 5.5 GB
Fits Get file →
Q3_K_L4.3 GB 5.8 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.6 GB 6.2 GB
Fits Get file →
IQ4_NL4.6 GB 6.2 GB
Fits Get file →
Q4_K_S4.6 GB 6.2 GB
Fits Get file →
Q4_K_M4.9 GB 6.4 GB
Fits Get file →
Q4_15.1 GB 6.7 GB
Fits Get file →
Q5_K_S5.5 GB 7.1 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.5 GB 8.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (4.87 GB file, ~6.4 GB memory). For 6 GB VRAM, use Q3_K_M (3.97 GB file, ~5.5 GB memory). For 4 GB VRAM, use IQ1_S (1.98 GB file, ~3.6 GB memory).

What GPU do you need for shisa 7b v1 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 IQ2_XXS (2.4 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.5 GB file, about 8.1 GB in use).

Which shisa 7b v1 i1 quant should you choose?

Q4_K_M is the usual starting point for shisa 7b v1 i1: it balances file size and quality well. Here it is a 4.9 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
Parameters7.96B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyShisa
Licenseapache-2.0
Downloads (HF)494
Last updated2025-12-05

Frequently asked questions about shisa 7b v1 i1

How much VRAM does shisa 7b v1 i1 need?

About 6.4 GB at Q4_K_M with an 8K context window. That is the 4.9 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 7b v1 i1 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of shisa 7b v1 i1 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.0 GB, IQ1_M is 2.1 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.7 GB and 19 more.

What context length does shisa 7b v1 i1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download shisa 7b v1 i1 GGUF?

The files are on Hugging Face in the mradermacher/shisa-7b-v1-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 7b v1 i1 use?

Hugging Face lists the license as apache-2.0. 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 7B v1 i1 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 6.4 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

No, Shisa 7B v1 i1 is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.

Other GGUFs of shisa-7b-v1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Shisa models

All Shisa →

Other small models

All small models →