What are the hardware requirements for Cagliostro V3.5?

Cagliostro V3.5 requires approximately 0.6 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 Cagliostro V3.5 and how large is it?

Cagliostro V3.5 is developed by bench-labs, a model with 146.4m 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 Cagliostro V3.5?

Cagliostro V3.5 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Cagliostro V3.5 by bench-labs — VRAM 0.6GB, 2K context

Name: Cagliostro V3.5
Author: bench-labs

Cagliostro V3.5 is an open-source language model by bench-labs. Features: 146.4m LLM, VRAM: 0.6GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.38.

Base-model Base model:bench-labs/cagliost... Base model:finetune:bench-labs... Cagliostro Custom code Dataset:huggingfacetb/cosmoped... Dataset:huggingfacetb/finemath Dataset:huggingfacetb/smollm-c... Dataset:huggingfacetb/smoltalk Dataset:mlfoundations/dclm-bas... Dataset:nvidia/openmathinstruc... En Language-model Region:us Safetensors Small-language-model

Model Card on HF 🤗: https://huggingface.co/bench-labs/cagliostro-v3.5

Cagliostro V3.5 Parameters and Internals

LLM Name	Cagliostro V3.5
Repository 🤗	https://huggingface.co/bench-labs/cagliostro-v3.5
Base Model(s)	Cagliostro V3 bench-labs/cagliostro-v3
Model Size	146.4m
Required VRAM	0.6 GB
Updated	2026-10-08
Maintainer	bench-labs
Model Type	cagliostro
Model Files	0.6 GB
Supported Languages	en
Model Architecture	CagliostroForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	5.14.1
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	32768

Rank the Cagliostro V3.5 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 Cagliostro V3.5

Best Alternatives	Context / RAM	Downloads	Likes
Cagliostro V3	2K / 0.6 GB	1182	30