What are the hardware requirements for Llama3.2 3B Esper2?

Llama3.2 3B Esper2 requires approximately 12.8 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama3.2 3B Esper2 and how large is it?

Llama3.2 3B Esper2 is developed by ValiantLabs, 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 Llama3.2 3B Esper2?

Llama3.2 3B Esper2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama3.2 3B Esper2 by ValiantLabs — VRAM 12.8GB, 128K context

Name: Llama3.2 3B Esper2
Author: ValiantLabs

Llama3.2 3B Esper2 is an open-source language model by ValiantLabs. Features: 3b LLM, VRAM: 12.8GB, Context: 128K, License: llama3.2, Instruction-Based, LLM Explorer Score: 0.17.

3b Architect Aws Azure Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... Chat Code Code-instruct Conversational Dataset:sequelbox/supernova Dataset:sequelbox/tachibana Dataset:sequelbox/titanium Dev-ops Developer En Engineer Esper Esper-2 Gcp Instruct Llama Llama-3 Llama-3-instruct Llama-3-instruct-3b Llama-3.2 Llama-3.2-instruct Llama-3.2-instruct-3b Model-index Python Region:us Safetensors Sharded Tensorflow Terraform Valiant Valiant-labs

Model Card on HF 🤗: https://huggingface.co/ValiantLabs/Llama3.2-3B-Esper2

Llama3.2 3B Esper2 Parameters and Internals

Model Type

text-generation

Additional Notes

Esper 2 improves performance through high quality DevOps, code, and chat data.

Training Details

Data Sources:

sequelbox/Titanium, sequelbox/Tachibana, sequelbox/Supernova

Methodology:

Finetuned on synthetic DevOps-instruct and code-instruct data generated with Llama 3.1 405b

Input Output

Input Format:

Llama 3.2 Instruct prompt format

Performance Tips:

Use the example script provided for general chat.

Release Notes

Version:

2024-10-03

Notes:

Release of Esper 2 for Llama 3.2 3b.

LLM Name	Llama3.2 3B Esper2
Repository 🤗	https://huggingface.co/ValiantLabs/Llama3.2-3B-Esper2
Base Model(s)	meta-llama/Llama-3.2-3B-Instruct meta-llama/Llama-3.2-3B-Instruct
Model Size	3b
Required VRAM	12.8 GB
Updated	2026-07-25
Maintainer	ValiantLabs
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-3 4.9 GB: 2-of-3 2.9 GB: 3-of-3
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	llama3.2
Context Length	131072
Model Max Length	131072
Transformers Version	4.45.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|eot_id\|>
Vocabulary Size	128256
Torch Data Type	float32

Rank the Llama3.2 3B Esper2 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 Llama3.2 3B Esper2

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3.2 3B Instruct	128K / 6.5 GB	1829572	2368
Llama 3.2 3B Instruct	128K / 6.5 GB	186207	96
Llama3.2 3B Manumit V1	128K / 6.4 GB	135	0
Llama 3.2 3B Instruct	128K / 6.5 GB	991	9
Alloma 3B Instruct	128K / 6.5 GB	55456	6
... V7 SFT 10voicebot Loopcleaned	128K / 6.5 GB	229	0
Llama 3.2 3B RP Toxic Fuse	128K / 6.4 GB	14	2
DeepSeek R1 Distill Llama 3B	128K / 6.5 GB	247	16
Schematron 3B	128K / 6.5 GB	969	336
ReasoningCore 3B T1 1	128K / 6.5 GB	8	1

Note: green Score (e.g. "73.2") means that the model is better than ValiantLabs/Llama3.2-3B-Esper2.