What are the hardware requirements for Vicuna 160M?

Vicuna 160M requires approximately 0.7 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Vicuna 160M and how large is it?

Vicuna 160M is developed by double7, a model with 160m 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 Vicuna 160M?

Vicuna 160M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Vicuna 160M by double7 — VRAM 0.7GB, 2K context

Name: Vicuna 160M
Author: double7

Vicuna 160M is an open-source language model by double7. Features: 160m LLM, VRAM: 0.7GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.1.

Arxiv:2401.06706 Dataset:anon8231489123/sharegp... En Endpoints compatible Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/double7/vicuna-160m

Vicuna 160M Parameters and Internals

Model Type

text generation

Additional Notes

Developed mainly as a base Small Speculative Model in the MCSD paper.

Supported Languages

en (proficient)

Training Details

Data Sources:

ShareGPT

Methodology:

Training setup follows the Vicuna suite

LLM Name	Vicuna 160M
Repository 🤗	https://huggingface.co/double7/vicuna-160m
Model Size	160m
Required VRAM	0.7 GB
Updated	2026-07-05
Maintainer	double7
Model Type	llama
Model Files	0.7 GB 0.0 GB
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float32

Rank the Vicuna 160M 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 Vicuna 160M

Best Alternatives	Context / RAM	Downloads	Likes
Llama 160M	2K / 0 GB	265161	37
Llama 160M Chat V1	2K / 0.7 GB	954	20
Mergekit Passthrough Jvjpjlj	2K / 0.4 GB	6	0
Tucano 160M	2K / 0.3 GB	351	4
TeenyTinyLlama Doc 160M	2K / 0 GB	10	0
Doctor Llama 160M	2K / 0 GB	5	0
TeenyTinyLlama 160M	2K / 0.7 GB	77	8
Onnx Llama 160M Chat V1	2K / GB	4	1
Spider Llama 160M	2K / 0.7 GB	6	0
Llama 160M Base	2K / 0 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than double7/vicuna-160m.