What are the hardware requirements for TinyLlama 1.1B Intermediate Step 480K 1T GGUF?

TinyLlama 1.1B Intermediate Step 480K 1T GGUF requires approximately 0.7 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 Intermediate Step 480K 1T GGUF and how large is it?

TinyLlama 1.1B Intermediate Step 480K 1T GGUF is developed by Trelis, 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.

How does TinyLlama 1.1B Intermediate Step 480K 1T GGUF perform on standard benchmarks?

TinyLlama 1.1B Intermediate Step 480K 1T GGUF has the following published scores: MMLU 25.85. Compare against reference models on this page or on the LLM Explorer leaderboards.

TinyLlama 1.1B Intermediate Step 480K 1T GGUF by Trelis — VRAM 0.7GB, 2K context

Name: TinyLlama 1.1B Intermediate Step 480K 1T GGUF
Author: Trelis

TinyLlama 1.1B Intermediate Step 480K 1T GGUF is an open-source language model by Trelis. Features: 1.1b LLM, VRAM: 0.7GB, Context: 2K, License: apache-2.0, Quantized, LLM Explorer Score: 0.13, Arc: 34.6, HellaSwag: 59.8, MMLU: 25.9, GSM8K: 1.7.

Dataset:bigcode/starcoderdata Dataset:cerebras/slimpajama-62... En Endpoints compatible Ggml Gguf Llama Quantized Region:us Tinyllama

Model Card on HF 🤗: https://huggingface.co/Trelis/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF

TinyLlama 1.1B Intermediate Step 480K 1T GGUF Parameters and Internals

Model Type

text generation

Additional Notes

Intermediate checkpoint with 480K steps and 1007B tokens.

Supported Languages

en (primary)

Training Details

Data Sources:

cerebras/SlimPajama-627B, bigcode/starcoderdata

Data Volume:

3 trillion tokens

Methodology:

same architecture and tokenizer as Llama 2

Training Time:

90 days

Hardware Used:

16 A100-40G GPUs

Model Architecture:

Llama 2 architecture

LLM Name	TinyLlama 1.1B Intermediate Step 480K 1T GGUF
Repository 🤗	https://huggingface.co/Trelis/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF
Base Model(s)	Tinyllama Lora Norobots smangrul/tinyllama_lora_norobots
Model Size	1.1b
Required VRAM	0.7 GB
Updated	2026-08-02
Maintainer	Trelis
Model Type	llama
Model Files	0.7 GB 0.0 GB
Supported Languages	en
GGML Quantization	Yes
GGUF Quantization	Yes
Quantization Type	gguf\|ggml
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.34.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the TinyLlama 1.1B Intermediate Step 480K 1T GGUF 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 Intermediate Step 480K 1T GGUF

Best Alternatives	Context / RAM	Downloads	Likes
TinyLlama 1.1B Chat V0.6	2K / 0.6 GB	3575	113
Medical Chatbot	2K / 0.7 GB	9	0
...u Chatvector Mlx Lm Chatalpaca	2K / 0.9 GB	38	0
...a Coder Math Ja Wikipedia V0.1	2K / 0.7 GB	172	1
...inyllama Coder Dolphin En V0.1	2K / 0.7 GB	101	1
...nyllama Coder Wizardlm En V0.1	2K / 0.7 GB	70	1
...ma Coder Python En Alpaca V0.1	2K / 0.7 GB	85	0
...on Ja Wikipedia Amenokaku V0.1	2K / 0.7 GB	31	0
Tinyllama Coder Math Ja V0.1	2K / 0.7 GB	22	0
...a Hate Speech Detector En V0.1	2K / 0.7 GB	32	0

Note: green Score (e.g. "73.2") means that the model is better than Trelis/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF.