KA

karasu 1.1B i1

KarasuGGUF by mradermacherUpdated 2024-11-02
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant0.3 GB
Quick answer

karasu 1.1B i1 needs about 1.4 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.3 GB (IQ1_S) to 0.9 GB (Q6_K).

Karasu 1.1B i1 – a compact Japanese‑focused LLaMA model

Karasu 1.1B i1 is a 1.1B parameter LLaMA model fine‑tuned on Japanese data. It offers a 2048 token context window and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Japanese language generation
  • Compact size for low‑resource setups
  • Easy integration with llama.cpp

Limits

  • No vision support
  • Context limited to 2048 tokens
  • Requires at least 1 GB VRAM for the smallest quant

Best for

  • Local Japanese chatbot
  • Text summarization on modest hardware
  • Rapid prototyping of Japanese LLM applications

Who it’s for. Developers and researchers needing a lightweight Japanese LLaMA model. It is suitable for edge deployments and educational projects where resource constraints are a priority.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.3 GB 0.8 GB
Fits Get file →
IQ1_M0.3 GB 0.8 GB
Fits Get file →
IQ2_XXS0.3 GB 0.9 GB
Fits Get file →
IQ2_XS0.4 GB 0.9 GB
Fits Get file →
IQ2_S0.4 GB 0.9 GB
Fits Get file →
IQ2_M0.4 GB 0.9 GB
Fits Get file →
Q2_K0.4 GB 1.0 GB
Fits Get file →
IQ3_XXS0.4 GB 1.0 GB
Fits Get file →
IQ3_XS0.5 GB 1.0 GB
Fits Get file →
Q3_K_S0.5 GB 1.0 GB
Fits Get file →
IQ3_S0.5 GB 1.0 GB
Fits Get file →
IQ3_M0.5 GB 1.1 GB
Fits Get file →
Q3_K_M0.5 GB 1.1 GB
Fits Get file →
Q3_K_L0.6 GB 1.1 GB
Fits Get file →
IQ4_XS0.6 GB 1.2 GB
Fits Get file →
Q4_00.6 GB 1.2 GB
Fits Get file →
Q4_00.6 GB 1.2 GB
Fits Get file →
Q4_00.6 GB 1.2 GB
Fits Get file →
Q4_00.6 GB 1.2 GB
Fits Get file →
Q4_K_S0.6 GB 1.2 GB
Fits Get file →
Q4_K_M0.7 GB 1.2 GB
Fits Get file →
Q5_K_S0.8 GB 1.3 GB
Fits Get file →
Q5_K_M0.8 GB 1.3 GB
Fits Get file →
Q6_K0.9 GB 1.4 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (file size 0.27 GB or 0.29 GB, memory 1 GB). If 12 GB VRAM is available, Q4_K_M (0.67 GB, 1.4 GB memory) offers a good balance of size and quality. Larger quants such as Q6_K (0.9 GB, 1.6 GB memory) provide higher fidelity but need more VRAM.

What GPU do you need for karasu 1.1B 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 Q6_K (0.9 GB file, about 1.6 GB in use).

Which karasu 1.1B i1 quant should you choose?

Q4_K_M is the usual starting point for karasu 1.1B i1: it balances file size and quality well. Here it is a 0.7 GB file.

If memory is tight, the smallest file is IQ1_S at 0.3 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

Architecturellama
Parameters1.1B
Layers22
Trained context2,048 tokens
KV cache (fp16)22 KB per token

Source

Quantized bymradermacher
FamilyKarasu
Licenseapache-2.0
Downloads (HF)602
Last updated2024-11-02

Frequently asked questions about karasu 1.1B i1

How much VRAM does karasu 1.1B i1 need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.7 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 karasu 1.1B i1 on an 8 GB GPU?

Yes, with Q6_K: the 0.9 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of karasu 1.1B i1 GGUF?

It depends on the quant: IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.3 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB, IQ2_M is 0.4 GB and 18 more.

What context length does karasu 1.1B i1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.

Where can I download karasu 1.1B i1 GGUF?

The files are on Hugging Face in the mradermacher/karasu-1.1B-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 karasu 1.1B 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 Karasu 1.1B i1 on 8 GB VRAM?

Yes, the smallest quants IQ1_S and IQ1_M require only about 1 GB VRAM at 8 k context.

Does Karasu 1.1B i1 support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of karasu-1.1B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Karasu models

All Karasu →

Other tiny models

All tiny models →