SA

Sarashina2.2 3b Instruct v0.1

SarashinaGGUF by tatsuyaaaaaaaUpdated 2025-10-03
Download on Hugging Face
Parameters3.36B
Context8K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

Sarashina2.2 3b Instruct v0.1 needs about 3.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 1.5 GB (IQ3_XS) to 6.7 GB (BF16).

Sarashina2.2 3b Instruct v0.1 – a Japanese instruction‑capable LLM

Sarashina2.2 3b Instruct v0.1 is a 3.36 billion‑parameter autoregressive model trained for Japanese instruction following. It supports tool usage and runs in GGUF format via llama.cpp. The model is licensed under MIT.

Good at

  • Japanese instruction following
  • Tool integration
  • Low‑memory inference

Limits

  • No vision support
  • Limited safety training
  • Context length 8192 tokens

Best for

  • Japanese chatbot development
  • Tool‑enabled task automation
  • Low‑budget inference

Who it’s for. Developers building Japanese language applications who need a lightweight instruction model. The model is suitable for projects that can handle its limited safety training and lack of vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XS1.5 GB 3.3 GB
Fits Get file →
IQ3_S1.5 GB 3.4 GB
Fits Get file →
IQ3_M1.6 GB 3.4 GB
Fits Get file →
IQ4_XS1.9 GB 3.7 GB
Fits Get file →
Q4_02.0 GB 3.8 GB
Fits Get file →
IQ4_NL2.0 GB 3.8 GB
Fits Get file →
Q4_K_S2.0 GB 3.8 GB
Fits Get file →
Q4_K_M2.1 GB 3.9 GB
Fits Get file →
Q5_02.3 GB 4.2 GB
Fits Get file →
Q5_K_S2.3 GB 4.2 GB
Fits Get file →
Q5_K_M2.4 GB 4.2 GB
Fits Get file →
Q5_12.5 GB 4.4 GB
Fits Get file →
Q6_K2.8 GB 4.6 GB
Fits Get file →
Q8_03.6 GB 5.4 GB
Fits Get file →
BF166.7 GB 8.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.07 GB, estimated 3.9 GB memory). For 4 GB VRAM, IQ3_XS (1.48 GB, 3.3 GB memory) or IQ3_S (1.55 GB, 3.4 GB memory) are recommended. Larger VRAM allows higher‑quality quants such as Q5_K_M or Q6_K.

What GPU do you need for Sarashina2.2 3b Instruct v0.1?

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 Q4_K_M (2.1 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 5.4 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (6.7 GB file, about 8.6 GB in use).

Which Sarashina2.2 3b Instruct v0.1 quant should you choose?

Q4_K_M is the usual starting point for Sarashina2.2 3b Instruct v0.1: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.6 GB, about 1.7 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 IQ3_XS at 1.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.36B
Layers32
Trained context8,192 tokens
KV cache (fp16)160 KB per token

Source

Quantized bytatsuyaaaaaaa
FamilySarashina
Licensemit
Downloads (HF)105
Last updated2025-10-03

Frequently asked questions about Sarashina2.2 3b Instruct v0.1

How much VRAM does Sarashina2.2 3b Instruct v0.1 need?

About 3.9 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Sarashina2.2 3b Instruct v0.1 on an 8 GB GPU?

Yes, with Q8_0: the 3.6 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sarashina2.2 3b Instruct v0.1 GGUF?

It depends on the quant: IQ3_XS is 1.5 GB, IQ3_S is 1.5 GB, IQ3_M is 1.6 GB, IQ4_XS is 1.9 GB, Q4_0 is 2.0 GB, IQ4_NL is 2.0 GB and 9 more.

What context length does Sarashina2.2 3b Instruct v0.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.3 GB at 8K and 1.3 GB at 8K.

Where can I download Sarashina2.2 3b Instruct v0.1 GGUF?

The files are on Hugging Face in the tatsuyaaaaaaa/sarashina2.2-3b-instruct-v0.1-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 Sarashina2.2 3b Instruct v0.1 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 3.9 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

No, it is an autoregressive language model with no vision capabilities.

What license applies to this model?

The model is released under the MIT License.

Other GGUFs of sarashina2.2-3b-instruct-v0.1

Similar models

Browse all →

More from tatsuyaaaaaaa

All by tatsuyaaaaaaa →

More Sarashina models

All Sarashina →

Other tiny models

All tiny models →