What are the hardware requirements for Meerkat 7B V1.0?

Meerkat 7B V1.0 requires approximately 28.9 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Meerkat 7B V1.0 and how large is it?

Meerkat 7B V1.0 is developed by dmis-lab, a model with 7b 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 Meerkat 7B V1.0?

Meerkat 7B V1.0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Meerkat 7B V1.0 by dmis-lab — VRAM 28.9GB, 32K context

Name: Meerkat 7B V1.0
Author: dmis-lab

Meerkat 7B V1.0 is an open-source language model by dmis-lab. Features: 7b LLM, VRAM: 28.9GB, Context: 32K, License: cc-by-nc-4.0, Instruction-Based, LLM Explorer Score: 0.13.

Arxiv:2009.03300 Arxiv:2009.13081 Arxiv:2203.14371 Arxiv:2402.18060 Chain-of-thought Conversational Endpoints compatible Instruct Instruction-tuned Medical Mistral Region:us Safetensors Sharded Small lm Synthetic data Tensorflow Usmle

Model Card on HF 🤗: https://huggingface.co/dmis-lab/meerkat-7b-v1.0

Meerkat 7B V1.0 Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

research, educational use

Applications:

medical instruction, clinical reasoning improvement

Primary Use Cases:

USMLE preparation, complex clinical case analysis

Considerations:

Model is intended for educational purposes and is not a substitute for professional medical advice.

Additional Notes

Meerkat-7B is instruction-tuned and integrates chain-of-thought reasoning for improved medical problem-solving.

Training Details

Data Sources:

18 medical textbooks, synthetic datasets

Model Architecture:

based on Mistral-7B-v0.1

Input Output

Input Format:

Input query should end with 'ASSISTANT:'

Accepted Modalities:

text

Output Format:

Generates text responses

LLM Name	Meerkat 7B V1.0
Repository 🤗	https://huggingface.co/dmis-lab/meerkat-7b-v1.0
Model Size	7b
Required VRAM	28.9 GB
Updated	2026-08-01
Maintainer	dmis-lab
Model Type	mistral
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-6 4.9 GB: 2-of-6 5.0 GB: 3-of-6 5.0 GB: 4-of-6 4.8 GB: 5-of-6 4.2 GB: 6-of-6 0.0 GB
Model Architecture	MistralForCausalLM
License	cc-by-nc-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float32

Rank the Meerkat 7B V1.0 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 Meerkat 7B V1.0

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	220	20
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
... Summarize 64K QLoRANET Merged	128K / 4.1 GB	8	0
...1 Summarize 64K LoRANET Merged	128K / 14.4 GB	12	0
Mistral 7B Instruct V0.2	32K / 14.4 GB	1115337	3184
Mistral 7B Instruct V0.1	32K / 14.4 GB	253629	1846
Mistral 7B Instruct V0.2	32K / 14.4 GB	1338	0
Lexi Coder V5.1	32K / 14.5 GB	197	0

Note: green Score (e.g. "73.2") means that the model is better than dmis-lab/meerkat-7b-v1.0.