What are the hardware requirements for Kunoichi 7B?

Kunoichi 7B requires approximately 14.5 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Kunoichi 7B and how large is it?

Kunoichi 7B is developed by SanjiWatsuki, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Kunoichi 7B perform on standard benchmarks?

Kunoichi 7B has the following published scores: MMLU 64.9. Compare against reference models on this page or on the LLM Explorer leaderboards.

Kunoichi 7B by SanjiWatsuki — VRAM 14.5GB, 8K context

Name: Kunoichi 7B
Author: SanjiWatsuki

Kunoichi 7B is an open-source language model by SanjiWatsuki. Features: 7b LLM, VRAM: 14.5GB, Context: 8K, License: cc-by-nc-4.0, LLM Explorer Score: 0.12, Arc: 68.7, HellaSwag: 87.1, MMLU: 64.9, GSM8K: 67.

Deploy:azure Endpoints compatible Merge Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/SanjiWatsuki/Kunoichi-7B

Kunoichi 7B Parameters and Internals

Model Type

general purpose, RP

Use Cases

Areas:

general purpose, role-playing (RP)

Applications:

ChatBot Arena, SillyTavern character card following

Additional Notes

Kunoichi-7B is particularly effective when employed within an 8k context window, although it can be used experimentally up to 16k using NTK RoPE alpha of 2.6.

Input Output

Input Format:

Custom format or Alpaca

Accepted Modalities:

text

Performance Tips:

Adjust temperature or min p to boost creativity or stability in SillyTavern configurations.

LLM Name	Kunoichi 7B
Repository 🤗	https://huggingface.co/SanjiWatsuki/Kunoichi-7B
Model Size	7b
Required VRAM	14.5 GB
Updated	2026-08-02
Maintainer	SanjiWatsuki
Model Type	mistral
Model Files	9.9 GB: 1-of-2 4.6 GB: 2-of-2
Model Architecture	MistralForCausalLM
License	cc-by-nc-4.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Kunoichi 7B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Kunoichi 7B

Model	Likes	Downloads	VRAM
Kunoichi 7B GGUF	37	2465	3 GB
Kunoichi 7B AWQ	8	1518	4 GB
Kunoichi 7B GGUF	1	314	2 GB
Kunoichi 7B GPTQ	16	30	4 GB

Best Alternatives to Kunoichi 7B

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	220	20
MegaBeam Mistral 7B 512K	512K / 14.4 GB	8470	54
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
MegaBeam Mistral 7B 300K	282K / 14.4 GB	3779	16
MegaBeam Mistral 7B 300K	282K / 14.4 GB	8018	17
Hebrew Mistral 7B 200K	256K / 30 GB	23	15
Astral 256K 7B	250K / 14.4 GB	9	0
Astral 256K 7B V2	250K / 14.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than SanjiWatsuki/Kunoichi-7B.