What are the hardware requirements for TinyLlama 1.1B Chat V1.0 GPTQ?

TinyLlama 1.1B Chat V1.0 GPTQ requires approximately 0.8 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TinyLlama 1.1B Chat V1.0 GPTQ and how large is it?

TinyLlama 1.1B Chat V1.0 GPTQ is developed by TheBloke, 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 Chat V1.0 GPTQ?

TinyLlama 1.1B Chat V1.0 GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TinyLlama 1.1B Chat V1.0 GPTQ by TheBloke — VRAM 0.8GB, 2K context

Name: TinyLlama 1.1B Chat V1.0 GPTQ
Author: TheBloke

TinyLlama 1.1B Chat V1.0 GPTQ is an open-source language model by TheBloke. Features: 1.1b LLM, VRAM: 0.8GB, Context: 2K, License: apache-2.0, Quantized, LLM Explorer Score: 0.17.

4-bit Base model:quantized:tinyllama... Base model:tinyllama/tinyllama... Conversational Dataset:bigcode/starcoderdata Dataset:cerebras/slimpajama-62... Dataset:openassistant/oasst to... En Gptq Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ

TinyLlama 1.1B Chat V1.0 GPTQ Parameters and Internals

Model Type

tinyllama

Additional Notes

The model is compact with 1.1B parameters, allowing it to be used in applications requiring limited computation and memory footprint.

Training Details

Data Sources:

cerebras/SlimPajama-627B, bigcode/starcoderdata, OpenAssistant/oasst_top1_2023-08-25

Methodology:

Following HF's Zephyr training recipe, initially fine-tuned on a variant of the UltraChat dataset, then further aligned with TRL's DPOTrainer on the UltraFeedback dataset.

Training Time:

90 days

Hardware Used:

16 A100-40G GPUs

Model Architecture:

Same architecture and tokenizer as Llama 2.

Input Output

Input Format:

<|system|> {system_message}~~ <|user|> {prompt}~~ <|assistant|>

LLM Name	TinyLlama 1.1B Chat V1.0 GPTQ
Repository 🤗	https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ
Model Name	Tinyllama 1.1B Chat v1.0
Model Creator	TinyLlama
Base Model(s)	TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama/TinyLlama-1.1B-Chat-v1.0
Model Size	1.1b
Required VRAM	0.8 GB
Updated	2026-05-14
Maintainer	TheBloke
Model Type	tinyllama
Model Files	0.8 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the TinyLlama 1.1B Chat V1.0 GPTQ 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 Chat V1.0 GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...inyLlama 1.1B Chat V1.0 Marlin	2K / 0.8 GB	13378	2
TinyLlama 1.1B Chat V0.3 GPTQ	2K / 0.8 GB	1081876	10
...Llama 1.1B Chat V1.0 GPTQ 4bit	2K / 0.8 GB	24697	0
....1B Chat V1.0 GPTQ Marlin 4bit	2K / 0.8 GB	13628	0
...inyLlama 1.1B Chat V1.0 Marlin	2K / 0.8 GB	3583	1
Tinyllama56k GPTQ	2K / 1.3 GB	7	0
...llama 24 Gptq 8bit Channelwise	2K / 1.2 GB	296	0
Tinyllama 24 Gptq 4bit G128	2K / 0.8 GB	7	0
Tinyllama 24 Gptq 8bit G128	2K / 1.3 GB	7	0
...llama 24 Gptq 4bit Channelwise	2K / 0.8 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ.