What are the hardware requirements for Llama 3.2 3B Instruct En Hi Merge 200K?

Llama 3.2 3B Instruct En Hi Merge 200K requires approximately 6.5 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 Llama 3.2 3B Instruct En Hi Merge 200K and how large is it?

Llama 3.2 3B Instruct En Hi Merge 200K is developed by taareshg, 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 En Hi Merge 200K?

Llama 3.2 3B Instruct En Hi Merge 200K 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 En Hi Merge 200K by taareshg — VRAM 6.5GB, 128K context

Name: Llama 3.2 3B Instruct En Hi Merge 200K
Author: taareshg

Llama 3.2 3B Instruct En Hi Merge 200K is an open-source language model by taareshg. Features: 3b LLM, VRAM: 6.5GB, Context: 128K, License: apache-2.0, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.16.

Merged Model 4bit Base model:finetune:unsloth/ll... Base model:unsloth/llama-3.2-3... Conversational En Endpoints compatible Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/taareshg/Llama-3.2-3B-Instruct-En-Hi-merge-200k

Llama 3.2 3B Instruct En Hi Merge 200K Parameters and Internals

LLM Name	Llama 3.2 3B Instruct En Hi Merge 200K
Repository 🤗	https://huggingface.co/taareshg/Llama-3.2-3B-Instruct-En-Hi-merge-200k
Base Model(s)	unsloth/Llama-3.2-3B-Instruct-bnb-4bit unsloth/Llama-3.2-3B-Instruct-bnb-4bit
Merged Model	Yes
Model Size	3b
Required VRAM	6.5 GB
Updated	2026-06-29
Maintainer	taareshg
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 1.5 GB: 2-of-2
Supported Languages	en
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.47.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|finetune_right_pad_id\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Llama 3.2 3B Instruct En Hi Merge 200K 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 Llama 3.2 3B Instruct En Hi Merge 200K

Best Alternatives	Context / RAM	Downloads	Likes
Llama3 Finetuned Id 16bit	128K / 6.5 GB	652	0
Slm Rag Sft Merged	128K / 6.5 GB	297	0
Llama3.2 3B Legal Id Ft	128K / 6.5 GB	264	0
...lama 3.2 3B Legal Assistant Id	128K / 6.5 GB	283	0
Fine Tuning LLM	128K / 6.5 GB	534	0
...Llama 3.2 3B Legal Chatbot Sft	128K / 6.5 GB	817	0
Cheese 3B	128K / 1.8 GB	249	1
Legal Llama3.2 3B Sft Id	128K / 6.5 GB	680	0
...gabl Legal Chatbot Llama3.2 3B	128K / 6.5 GB	528	0
Llama 3.2 3B Legal Id Sft	128K / 6.5 GB	236	0

Note: green Score (e.g. "73.2") means that the model is better than taareshg/Llama-3.2-3B-Instruct-En-Hi-merge-200k.