What are the hardware requirements for Llama 3.2 3B Instruct DSpark?

Llama 3.2 3B Instruct DSpark requires approximately 1.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 3.2 3B Instruct DSpark and how large is it?

Llama 3.2 3B Instruct DSpark is developed by rasyosef, a model with 3b 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 Llama 3.2 3B Instruct DSpark?

Llama 3.2 3B Instruct DSpark is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 3.2 3B Instruct DSpark by rasyosef — VRAM 1.5GB

Name: Llama 3.2 3B Instruct DSpark
Author: rasyosef

Llama 3.2 3B Instruct DSpark is an open-source language model by rasyosef. Features: 3b LLM, VRAM: 1.5GB, License: llama3.2, Instruction-Based, LLM Explorer Score: 0.28.

Base model:finetune:unsloth/ll... Base model:unsloth/llama-3.2-3... Custom code Draft-model Dspark Endpoints compatible Instruct Region:us Safetensors Speculative-decoding Speculators Vllm

Model Card on HF 🤗: https://huggingface.co/rasyosef/Llama-3.2-3B-Instruct-DSpark

Llama 3.2 3B Instruct DSpark Parameters and Internals

LLM Name	Llama 3.2 3B Instruct DSpark
Repository 🤗	https://huggingface.co/rasyosef/Llama-3.2-3B-Instruct-DSpark
Base Model(s)	unsloth/Llama-3.2-3B-Instruct unsloth/Llama-3.2-3B-Instruct
Model Size	3b
Required VRAM	1.5 GB
Updated	2026-10-08
Maintainer	rasyosef
Instruction-Based	Yes
Model Files	1.5 GB
Model Architecture	DSparkDraftModel
License	llama3.2
Transformers Version	5.16.1

Rank the Llama 3.2 3B Instruct DSpark 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