What are the hardware requirements for Mistral Small 3.1 DRAFT 0.5B?

Mistral Small 3.1 DRAFT 0.5B requires approximately 1.2 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 Small 3.1 DRAFT 0.5B and how large is it?

Mistral Small 3.1 DRAFT 0.5B is developed by alamios, a model with 24b 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 Small 3.1 DRAFT 0.5B?

Mistral Small 3.1 DRAFT 0.5B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mistral Small 3.1 DRAFT 0.5B by alamios — VRAM 1.2GB, 32K context

Name: Mistral Small 3.1 DRAFT 0.5B
Author: alamios

Mistral Small 3.1 DRAFT 0.5B is an open-source language model by alamios. Features: 24b LLM, VRAM: 1.2GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.19.

Base model:alamios/qwenstral-s... Base model:finetune:alamios/qw... Conversational Dataset:alamios/mistral-small-... De En Endpoints compatible Es Fr Instruct It Mistral Mistral-small Mistral-small-3.1 Pt Qwen Qwen2 Qwen2.5 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/alamios/Mistral-Small-3.1-DRAFT-0.5B

Mistral Small 3.1 DRAFT 0.5B Parameters and Internals

LLM Name	Mistral Small 3.1 DRAFT 0.5B
Repository 🤗	https://huggingface.co/alamios/Mistral-Small-3.1-DRAFT-0.5B
Base Model(s)	alamios/Qwenstral-Small-3.1-0.5B alamios/Qwenstral-Small-3.1-0.5B
Model Size	24b
Required VRAM	1.2 GB
Updated	2026-07-24
Maintainer	alamios
Model Type	qwen2
Instruction-Based	Yes
Model Files	1.2 GB
Supported Languages	en fr de es it pt
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.48.3
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Mistral Small 3.1 DRAFT 0.5B 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