What are the hardware requirements for MAmmoTH2 8B Plus?

MAmmoTH2 8B Plus requires approximately 16.1 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MAmmoTH2 8B Plus and how large is it?

MAmmoTH2 8B Plus is developed by TIGER-Lab, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does MAmmoTH2 8B Plus perform on standard benchmarks?

MAmmoTH2 8B Plus has the following published scores: MMLU 64.3. Compare against reference models on this page or on the LLM Explorer leaderboards.

MAmmoTH2 8B Plus by TIGER-Lab — VRAM 16.1GB, 8K context

Name: MAmmoTH2 8B Plus
Author: TIGER-Lab

MAmmoTH2 8B Plus is an open-source language model by TIGER-Lab. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: mit, LLM Explorer Score: 0.17, Arc: 62.3, HellaSwag: 79.8, MMLU: 64.3, GSM8K: 70.7.

Arxiv:2405.03548 Conversational Dataset:tiger-lab/webinstructs... Deploy:azure En Endpoints compatible Eval-results Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TIGER-Lab/MAmmoTH2-8B-Plus

MAmmoTH2 8B Plus Parameters and Internals

Model Type

Language Model, Instruction Tuning

Use Cases

Areas:

Research, Commercial applications

Applications:

Chatbots, Reasoning tasks

Limitations:

Performance may vary based on the complexity and specifics of the math problem., Not all mathematical fields can be covered comprehensively.

Supported Languages

en (Proficient)

Training Details

Data Sources:

https://huggingface.co/datasets/TIGER-Lab/WebInstructSub

Methodology:

The models are fine-tuned with the WEBINSTRUCT dataset using the original Llama-3, Mistral, and Mistal models as base models.

Input Output

Accepted Modalities:

text

LLM Name	MAmmoTH2 8B Plus
Repository 🤗	https://huggingface.co/TIGER-Lab/MAmmoTH2-8B-Plus
Model Size	8b
Required VRAM	16.1 GB
Updated	2026-08-07
Maintainer	TIGER-Lab
Model Type	llama
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.2 GB: 4-of-4
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	mit
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|eot_id\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the MAmmoTH2 8B Plus 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 MAmmoTH2 8B Plus

Best Alternatives	Context / RAM	Downloads	Likes
...otron 8B UltraLong 4M Instruct	4192K / 32.1 GB	1135	125
UltraLong Thinking	4192K / 16.1 GB	2	3
...a 3.1 8B UltraLong 4M Instruct	4192K / 32.1 GB	176	24
...a 3.1 8B UltraLong 2M Instruct	2096K / 32.1 GB	875	9
...otron 8B UltraLong 2M Instruct	2096K / 32.1 GB	124	18
Cthulhu 8B V1.4	1048K / 16.1 GB	10	10
...raLong 1M Instruct Abliterated	1048K / 32.1 GB	4	9
...a 3.1 8B UltraLong 1M Instruct	1048K / 32.1 GB	1387	29
...otron 8B UltraLong 1M Instruct	1048K / 32.1 GB	702	59
...xis Bookwriter Llama3.1 8B Sft	1048K / 16.1 GB	25	4

Note: green Score (e.g. "73.2") means that the model is better than TIGER-Lab/MAmmoTH2-8B-Plus.