What are the hardware requirements for Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2?

Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2 requires approximately 9.9 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 Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2 and how large is it?

Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2 is developed by Nexesenex, 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 Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2?

Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2 by Nexesenex — VRAM 9.9GB, 32K context

Name: Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2
Author: Nexesenex

Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2 is an open-source language model by Nexesenex. Features: 7b LLM, VRAM: 9.9GB, Context: 32K, License: apache-2.0, MoE, Quantized, Fine-Tuned, Instruction-Based, Merged, LLM Explorer Score: 0.1.

Merged Model Arxiv:2310.06825 Conversational Exl2 Finetuned Instruct Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Nexesenex/Mistral-7B-Instruct-v0.2-2x7B-MoE-6.0bpw-h6-exl2

Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2 Parameters and Internals

Model Type

text generation, instruction fine-tuned

Use Cases

Limitations:

The model does not have any moderation mechanisms., It's a quick demonstration; improvements are expected in future iterations.

Training Details

Methodology:

Instruction fine-tuning

Model Architecture:

Transformer model with Grouped-Query Attention, Sliding-Window Attention, and Byte-fallback BPE tokenizer

Input Output

Input Format:

Use `[INST]` and `[/INST]` tokens to enclose instructions.

LLM Name	Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2
Repository 🤗	https://huggingface.co/Nexesenex/Mistral-7B-Instruct-v0.2-2x7B-MoE-6.0bpw-h6-exl2
Merged Model	Yes
Model Size	7b
Required VRAM	9.9 GB
Updated	2026-07-31
Maintainer	Nexesenex
Model Type	mixtral
Instruction-Based	Yes
Model Files	8.6 GB: 1-of-2 1.3 GB: 2-of-2
Quantization Type	exl2
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2 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 Mistral 7B Instruct V0.2 2x7B MoE 6.0bpw H6 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
Mini Mixtral V0.2	32K / 25.8 GB	3923	4
OpenMistral MoE	32K / 48.3 GB	1218	0
Multilingual Mistral	32K / 93.5 GB	65	2
Magiq 3	32K / 37.1 GB	5	3
FNCARL9000	32K / 48.3 GB	8	0
Bigstral 12B 32K 8xMoE	32K / 163.3 GB	12	2
CollAIborate4x7B	32K / 48.7 GB	6	1
CollAIborate4x7B	32K / 48.7 GB	1	1
OpenMistral MoE	32K / 48.3 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than Nexesenex/Mistral-7B-Instruct-v0.2-2x7B-MoE-6.0bpw-h6-exl2.