SH

Shisa V1 7B V2.1

ShisaGGUF by mradermacherUpdated 2025-12-08
Download on Hugging Face
Parameters7.96B
Context32K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

Shisa V1 7B V2.1 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 V1 7B V2.1 – a 7.96B parameter Japanese‑English model

Shisa V1 7B V2.1 is a 7.96B parameter model trained on mixed EN/JA data. It uses a 32768 token context window and is released under the apache-2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Japanese text generation
  • English text generation
  • Efficient tokenization

Limits

  • No vision support
  • Large VRAM required for higher quants
  • No mixture of experts

Best for

  • Chatbots needing Japanese support
  • Japanese‑English translation tasks
  • Local inference on high‑VRAM GPUs

Who it’s for. Developers and researchers who need a Japanese‑English LLM that can run locally. The model is suitable for applications that require a moderate‑size model with a large context window.

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 (file size 4.87 GB, estimated 6.4 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (5.68 GB, 7.3 GB memory) or Q6_K (6.54 GB, 8.1 GB memory). Lower‑bit IQ1_S or IQ1_M (1.98 GB, 3.6 GB or 2.12 GB, 3.7 GB) fit on 4 GB VRAM but use more CPU memory.

What GPU do you need for Shisa V1 7B V2.1?

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 V1 7B V2.1 quant should you choose?

Q4_K_M is the usual starting point for Shisa V1 7B V2.1: 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)453
Last updated2025-12-08

Frequently asked questions about Shisa V1 7B V2.1

How much VRAM does Shisa V1 7B V2.1 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 V1 7B V2.1 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 V1 7B V2.1 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 V1 7B V2.1 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 V1 7B V2.1 GGUF?

The files are on Hugging Face in the mradermacher/shisa-v1-7b-v2.1-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 V1 7B V2.1 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 V1 7B V2.1 on 8 GB VRAM?

Yes, the Q4_K_M quant uses 4.87 GB file size and requires about 6.4 GB VRAM at 8k context.

What is the smallest quant I can use?

The smallest quant is unknown, but the smallest listed is IQ1_S at 1.98 GB file size and 3.6 GB VRAM.

Does this model support vision tasks?

No, the model has no vision support.

Other GGUFs of shisa-v1-7b-v2.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Shisa models

All Shisa →

Other small models

All small models →