What are the hardware requirements for TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2?

TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2 requires approximately 0.5 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 TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2 and how large is it?

TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2 is developed by LoneStriker, a model with 1.1b 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 TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2?

TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2 by LoneStriker — VRAM 0.5GB, 32K context

Name: TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2
Author: LoneStriker

TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 1.1b LLM, VRAM: 0.5GB, Context: 32K, Quantized, Instruction-Based, LLM Explorer Score: 0.11.

Conversational Dataset:doctor-shotgun/capybar... Dataset:doctor-shotgun/no-robo... Dataset:huggingfaceh4/no robot... Dataset:jondurbin/airoboros-3.... Dataset:ldjnr/capybara Dataset:ldjnr/verified-camel Dataset:unalignment/toxic-dpo-... En Exl2 Instruct Llama Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/LoneStriker/TinyLlama-1.1B-32k-Instruct-3.0bpw-h6-exl2

TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2 Parameters and Internals

Model Type

text generation

Training Details

Data Sources:

LDJnr/Capybara, jondurbin/airoboros-3.2, unalignment/toxic-dpo-v0.1, LDJnr/Verified-Camel, HuggingFaceH4/no_robots, Doctor-Shotgun/no-robots-sharegpt, Doctor-Shotgun/capybara-sharegpt

Methodology:

The model was trained as a full finetune for 3 epochs using a single A100 GPU for around 3.5 hours.

Training Time:

3.5 hours

Hardware Used:

A100 GPU

Input Output

Input Format:

A modified multi-turn Alpaca instruction format: ### Instruction: {system prompt} ### Input: {user message} ### Response: {model response} ### Input: {user message} ### Response: {model response} (etc.)

LLM Name	TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2
Repository 🤗	https://huggingface.co/LoneStriker/TinyLlama-1.1B-32k-Instruct-3.0bpw-h6-exl2
Model Size	1.1b
Required VRAM	0.5 GB
Updated	2026-07-24
Maintainer	LoneStriker
Model Type	llama
Instruction-Based	Yes
Model Files	0.5 GB
Supported Languages	en
Quantization Type	exl2
Model Architecture	LlamaForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2 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 TinyLlama 1.1B 32K Instruct 3.0bpw H6 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
...1B 32K Instruct 8.0bpw H8 EXL2	32K / 1.2 GB	6	1
...nish English Asistant 16bit V2	2K / 2.2 GB	14	0
TinyKiller NSFW DPO 1.1B	32K / 2.2 GB	12	0
TinyLlama 1.1B 32K Instruct	32K / 2.2 GB	2806	13
...llama 1.1B 16K Instructions V4	32K / 2.2 GB	8	0
Palmer 002 32K	32K / 2.2 GB	9	0
...lama 1.1B 16K Instructions Rag	32K / 2.2 GB	25	0
...diate 1.5T PTBR Instruct V3 8K	8K / 2.2 GB	11	8
Tinyllama Coder Py 4bit V10	4K / 0.7 GB	65	0
TinyLlama 1.1B Instruct 3T	4K / 2.2 GB	56	0

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/TinyLlama-1.1B-32k-Instruct-3.0bpw-h6-exl2.