What are the hardware requirements for Tinydolphin 3x MoE Samantha Chatml Therabot?

Tinydolphin 3x MoE Samantha Chatml Therabot requires approximately 5.2 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Tinydolphin 3x MoE Samantha Chatml Therabot and how large is it?

Tinydolphin 3x MoE Samantha Chatml Therabot is developed by jtatman, a model with 2.6b 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 Tinydolphin 3x MoE Samantha Chatml Therabot?

Tinydolphin 3x MoE Samantha Chatml Therabot is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tinydolphin 3x MoE Samantha Chatml Therabot by jtatman — VRAM 5.2GB, 4K context

Name: Tinydolphin 3x MoE Samantha Chatml Therabot
Author: jtatman

Tinydolphin 3x MoE Samantha Chatml Therabot is an open-source language model by jtatman. Features: 2.6b LLM, VRAM: 5.2GB, Context: 4K, MoE, LLM Explorer Score: 0.11.

Arxiv:1910.09700 Endpoints compatible Mixtral Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jtatman/tinydolphin-3x-MoE-samantha-chatml-therabot

Tinydolphin 3x MoE Samantha Chatml Therabot Parameters and Internals

LLM Name	Tinydolphin 3x MoE Samantha Chatml Therabot
Repository 🤗	https://huggingface.co/jtatman/tinydolphin-3x-MoE-samantha-chatml-therabot
Model Size	2.6b
Required VRAM	5.2 GB
Updated	2026-04-21
Maintainer	jtatman
Model Type	mixtral
Model Files	5.0 GB: 1-of-2 0.2 GB: 2-of-2
Model Architecture	MixtralForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.38.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	32064
Torch Data Type	float16

Rank the Tinydolphin 3x MoE Samantha Chatml Therabot 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 Tinydolphin 3x MoE Samantha Chatml Therabot

Best Alternatives	Context / RAM	Downloads	Likes
TinyExperts V0 4x1B	32K / 5.2 GB	1298	0
...oE 2.6B A0.6B Instruct Preview	4K / 5.2 GB	1764	11
Aquif 3.5 A0.6B Preview	4K / 5.2 GB	17	0
EuroMoE 2.6B A0.6B 2512	4K / 5.2 GB	139	11
TinyEnsemble 3x1.1B TinyMoE	4K / 5.3 GB	6	0
...Oasst2 ChatML Cluster 3 2 1 V1	4K / 5.2 GB	6	3
LiteLlamix 8x460M 1T	1K / 5.2 GB	9	4

Note: green Score (e.g. "73.2") means that the model is better than jtatman/tinydolphin-3x-MoE-samantha-chatml-therabot.