What are the hardware requirements for Llama 3 13B Instruct Ft?

Llama 3 13B Instruct Ft requires approximately 26.1 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 3 13B Instruct Ft and how large is it?

Llama 3 13B Instruct Ft is developed by elinas, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama 3 13B Instruct Ft perform on standard benchmarks?

Llama 3 13B Instruct Ft has the following published scores: MMLU 65.42. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 3 13B Instruct Ft by elinas — VRAM 26.1GB, 8K context

Name: Llama 3 13B Instruct Ft
Author: elinas

Llama 3 13B Instruct Ft is an open-source language model by elinas. Features: 13b LLM, VRAM: 26.1GB, Context: 8K, License: llama3, Instruction-Based, LLM Explorer Score: 0.14, Arc: 58.5, HellaSwag: 77.5, MMLU: 65.4, GSM8K: 49.7.

Base model:elinas/llama-3-13b-... Base model:finetune:elinas/lla... Conversational Dataset:chat-error/pure-dove-s... Endpoints compatible Instruct Llama Merge Mergekit Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/elinas/Llama-3-13B-Instruct-ft

Llama 3 13B Instruct Ft Parameters and Internals

Model Type

text generation

Additional Notes

This model was an experiment focusing on a 'mid' sized model to test finetuning using a small dataset. The next steps involve further testing and potentially larger datasets. Sample packing and padding were disabled to reduce VRAM. Performance was tested with RoPE up to 32k.

Training Details

Data Sources:

Chat-Error/Pure-dove-sharegpt

Data Volume:

8192 context length

Methodology:

QLoRA finetuning

Context Length:

8192

Training Time:

4h 12m 13s

Hardware Used:

3x3090 GPUs

LLM Name	Llama 3 13B Instruct Ft
Repository 🤗	https://huggingface.co/elinas/Llama-3-13B-Instruct-ft
Base Model(s)	Llama 3 13B Instruct elinas/Llama-3-13B-Instruct
Model Size	13b
Required VRAM	26.1 GB
Updated	2026-07-12
Maintainer	elinas
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-6 5.0 GB: 2-of-6 4.9 GB: 3-of-6 5.0 GB: 4-of-6 4.9 GB: 5-of-6 1.3 GB: 6-of-6
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Llama 3 13B Instruct Ft 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 13B Instruct Ft

Best Alternatives	Context / RAM	Downloads	Likes
NexusRaven V2 13B	16K / 26 GB	105	472
CodeLlama 13B Instruct Hf	16K / 26 GB	2469	160
CodeLlama 13B MORepair	16K / 26 GB	9	2
CodeLlama 13B Instruct Hf	16K / 26 GB	369	29
TableLLM 13B	16K / 26 GB	98	34
NexusRaven 13B	16K / 26 GB	37	106
Panda Coder 13B	16K / 26 GB	11	14
... Llama 2 13B Instruct Text2sql	16K / 26 GB	8	28
Gen Sim	16K / 0.3 GB	4	3
Llama 2 13B SoftwareReq	8K / 16.1 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than elinas/Llama-3-13B-Instruct-ft.