What are the hardware requirements for Charllama 35M?

Charllama 35M requires approximately 0.1 GB of VRAM and supports a context window of 0.5K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Charllama 35M and how large is it?

Charllama 35M is developed by inkoziev, a model with 35m 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 Charllama 35M?

Charllama 35M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Charllama 35M by inkoziev — VRAM 0.1GB, 0.5K context

Name: Charllama 35M
Author: inkoziev

Charllama 35M is an open-source language model by inkoziev. Features: 35m LLM, VRAM: 0.1GB, Context: 0.5K, License: openrail, LLM Explorer Score: 0.08.

Arxiv:2302.13971 Deploy:azure Endpoints compatible Llama Pytorch Region:us Ru

Model Card on HF 🤗: https://huggingface.co/inkoziev/charllama-35M

Charllama 35M Parameters and Internals

Model Type

causal-lm

Use Cases

Areas:

Generative spell-checkers, Text classification, Text transcription, Spelling error detection

Primary Use Cases:

Replacement for TfidfVectorizer(analyzer='char')

Additional Notes

This model has significant exposure to poetic formats due to its training corpus, which may affect downstream tasks.

Supported Languages

ru (Only)

Training Details

Data Sources:

project \

Data Volume:

80B tokens

Model Architecture:

[LLaMa architecture](https://arxiv.org/abs/2302.13971)

LLM Name	Charllama 35M
Repository 🤗	https://huggingface.co/inkoziev/charllama-35M
Model Size	35m
Required VRAM	0.1 GB
Updated	2026-07-11
Maintainer	inkoziev
Model Type	llama
Model Files	0.1 GB
Supported Languages	ru
Model Architecture	LlamaForCausalLM
License	openrail
Context Length	512
Model Max Length	512
Transformers Version	4.28.1
Vocabulary Size	658
Torch Data Type	float32

Rank the Charllama 35M 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 Charllama 35M

Best Alternatives	Context / RAM	Downloads	Likes
SimpleStories 35M	0.5K / 0.1 GB	185	1

Note: green Score (e.g. "73.2") means that the model is better than inkoziev/charllama-35M.