What are the hardware requirements for Dokichat 100M?

Dokichat 100M requires approximately 0.2 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 Dokichat 100M and how large is it?

Dokichat 100M is developed by Dokitek, a model with 100m 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 Dokichat 100M?

Dokichat 100M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Dokichat 100M by Dokitek — VRAM 0.2GB, 2K context

Name: Dokichat 100M
Author: Dokitek

Dokichat 100M is an open-source language model by Dokitek. Features: 100m LLM, VRAM: 0.2GB, Context: 2K, License: apache-2.0.

Arxiv:2402.00786 Arxiv:2402.14905 Arxiv:2502.10361 Dataset:epfml/fineweb2-hq Endpoints compatible Fr French Qwen3 Region:us Safetensors Small-language-model Trained-from-scratch

Model Card on HF 🤗: https://huggingface.co/Dokitek/Dokichat-100M

Dokichat 100M Parameters and Internals

LLM Name	Dokichat 100M
Repository 🤗	https://huggingface.co/Dokitek/Dokichat-100M
Model Size	100m
Required VRAM	0.2 GB
Updated	2026-11-04
Maintainer	Dokitek
Model Type	qwen3
Model Files	0.2 GB
Supported Languages	fr
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Dokichat 100M 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 Dokichat 100M

Best Alternatives	Context / RAM	Downloads	Likes
Vertex 0.6 100M 8192 Instruct	8K / 0.4 GB	373	0
...rtex 0.6 100M 8192 Instruct V2	8K / 0.4 GB	271	0
Vertex 0.6 100M 8192 Ctx Base	8K / 0.4 GB	162	2
Luno 100M Lightweight	2K / 0.2 GB	594	1
Supra2 100M Base ONNX	2K / GB	307	1
Supra2 100M Base	2K / 0.4 GB	110	21
Supra2 100M Instruct	2K / 0.2 GB	1462	34
CalmaCatCoder Next Mini	1K / 0.2 GB	306	1

Note: green Score (e.g. "73.2") means that the model is better than Dokitek/Dokichat-100M.