What are the hardware requirements for Vigogne 2 7B Instruct?

Vigogne 2 7B Instruct requires approximately 13.5 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 Vigogne 2 7B Instruct and how large is it?

Vigogne 2 7B Instruct is developed by bofenghuang, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Vigogne 2 7B Instruct perform on standard benchmarks?

Vigogne 2 7B Instruct has the following published scores: MMLU 47.17. Compare against reference models on this page or on the LLM Explorer leaderboards.

Vigogne 2 7B Instruct by bofenghuang — VRAM 13.5GB, 2K context

Name: Vigogne 2 7B Instruct
Author: bofenghuang

Vigogne 2 7B Instruct is an open-source language model by bofenghuang. Features: 7b LLM, VRAM: 13.5GB, Context: 2K, Instruction-Based, LLM Explorer Score: 0.1, Arc: 56.2, HellaSwag: 80, MMLU: 47.2, GSM8K: 3.8.

Fr Instruct Llama Llama2 Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/bofenghuang/vigogne-2-7b-instruct

Vigogne 2 7B Instruct Parameters and Internals

Model Type

text generation

Additional Notes

Vigogne-2-7B-Instruct is a Llama-2 based model fine-tuned for French instructions.

Supported Languages

French (high)

LLM Name	Vigogne 2 7B Instruct
Repository 🤗	https://huggingface.co/bofenghuang/vigogne-2-7b-instruct
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-08-04
Maintainer	bofenghuang
Model Type	llama
Instruction-Based	Yes
Model Files	2.0 GB: 1-of-7 2.0 GB: 2-of-7 2.0 GB: 3-of-7 2.0 GB: 4-of-7 1.9 GB: 5-of-7 1.9 GB: 6-of-7 1.7 GB: 7-of-7
Supported Languages	fr
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.32.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Vigogne 2 7B Instruct 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

Quantized Models of the Vigogne 2 7B Instruct

Model	Likes	Downloads	VRAM
Vigogne 2 7B Instruct GGUF	4	422	2 GB
Vigogne 2 7B Instruct GPTQ	3	12	3 GB
Vigogne 2 7B Instruct GGML	2	4	2 GB

Best Alternatives to Vigogne 2 7B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
124	1024K / 16.1 GB	93	0
A5.4	1024K / 16.1 GB	12	0
A3.4	1024K / 16.1 GB	13	0
A2.4	1024K / 16.1 GB	12	0
... Qwen2.5llamaify 7B V23.1 200K	195K / 15.2 GB	29	5
Salamandra 7B Instruct 2606	160K / 15.6 GB	9217	3
SuperNeuralDreadDevil 8B	128K / 16.1 GB	46	1
Falcon3 7B Instruct	32K / 14.8 GB	11749	80
...truct Auto Round Int4 Gs64 Sym	32K / 6.9 GB	48	1
Falcon3 Jessi V0.4 7B Slerp	32K / 14.9 GB	34	9

Note: green Score (e.g. "73.2") means that the model is better than bofenghuang/vigogne-2-7b-instruct.