What are the hardware requirements for Kisoku 1.6B?

Kisoku 1.6B requires approximately 3.2 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Kisoku 1.6B and how large is it?

Kisoku 1.6B is developed by 0arch-io, a model with 1.6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Kisoku 1.6B?

Kisoku 1.6B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Kisoku 1.6B by 0arch-io — VRAM 3.2GB, 128K context

Name: Kisoku 1.6B
Author: 0arch-io

Kisoku 1.6B is an open-source language model by 0arch-io. Features: 1.6b LLM, VRAM: 3.2GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.26.

Conversational Dataset:bigcode/starcoderdata Dataset:deepmind/pg19 Dataset:huggingfacetb/finemath Dataset:ifm/megamath Dataset:nvidia/nemotron-cc-mat... Dataset:nvidia/nemotron-cc-v2.... Dataset:open-thoughts/openthou... Dataset:open-web-math/open-web... Dataset:openbmb/ultra-fineweb Dataset:princeton-nlp/prolong-... En Endpoints compatible From-scratch Kisoku Long-context Pretrained Qwen3 Region:us Safetensors Tpu

Model Card on HF 🤗: https://huggingface.co/0arch-io/kisoku-1.6b

Kisoku 1.6B Parameters and Internals

LLM Name	Kisoku 1.6B
Repository 🤗	https://huggingface.co/0arch-io/kisoku-1.6b
Base Model(s)	none /none
Model Size	1.6b
Required VRAM	3.2 GB
Updated	2026-10-22
Maintainer	0arch-io
Model Type	qwen3
Model Files	3.2 GB
Supported Languages	en
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.57.6
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256

Rank the Kisoku 1.6B 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

Best Alternatives to Kisoku 1.6B

Best Alternatives	Context / RAM	Downloads	Likes
Kisoku 1.6B Preview	4K / 3.2 GB	225	0

Note: green Score (e.g. "73.2") means that the model is better than 0arch-io/kisoku-1.6b.