What are the hardware requirements for Mixtral Quantized?

Mixtral Quantized requires approximately 14.4 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 Mixtral Quantized and how large is it?

Mixtral Quantized is developed by alquimista888, a model with 7.2b 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 Mixtral Quantized?

Mixtral Quantized is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mixtral Quantized by alquimista888 — VRAM 14.4GB, 32K context

Name: Mixtral Quantized
Author: alquimista888

Mixtral Quantized is an open-source language model by alquimista888. Features: 7.2b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, Quantized, Fine-Tuned, LLM Explorer Score: 0.12.

Arxiv:2310.06825 Conversational Endpoints compatible Finetuned Gguf Mistral Pytorch Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/alquimista888/mixtral_quantized

Mixtral Quantized Parameters and Internals

Model Type

text-generation

Additional Notes

The model does not have any moderation mechanisms.

Training Details

Methodology:

Instruction fine-tuning

Context Length:

32000

Input Output

Input Format:

[INST] {prompt} [/INST]

Output Format:

Text

LLM Name	Mixtral Quantized
Repository 🤗	https://huggingface.co/alquimista888/mixtral_quantized
Model Size	7.2b
Required VRAM	14.4 GB
Updated	2026-07-16
Maintainer	alquimista888
Model Type	mistral
Model Files	4.4 GB 4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3 4.9 GB: 1-of-3 5.0 GB: 2-of-3 5.1 GB: 3-of-3
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Mixtral Quantized 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 Mixtral Quantized

Best Alternatives	Context / RAM	Downloads	Likes
Spydaz Web AGI DeepThink	128K / 14.4 GB	14	1
...daz Web AI Pre Train Align 004	128K / 14.4 GB	28	0
Zion Alpha	32K / 14.4 GB	57	4
LCARS AI 001	32K / 14.4 GB	14	4
Mayonnaise 4in1 02	32K / 14.4 GB	105	0
Zsql En Postgres	32K / 14.4 GB	64	5
MHENNlitv3	32K / 28.9 GB	12	0
MHENNlitv2	32K / 28.9 GB	17	0
MHENNcodemathv2	32K / 28.9 GB	10	0
MHENNcodemath	32K / 28.9 GB	17	0

Note: green Score (e.g. "73.2") means that the model is better than alquimista888/mixtral_quantized.