What are the hardware requirements for Llama 3 15B Instruct Ft V2 AWQ?

Llama 3 15B Instruct Ft V2 AWQ requires approximately 9.4 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 15B Instruct Ft V2 AWQ and how large is it?

Llama 3 15B Instruct Ft V2 AWQ is developed by solidrust, a model with 15b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama 3 15B Instruct Ft V2 AWQ perform on standard benchmarks?

Llama 3 15B Instruct Ft V2 AWQ has the following published scores: MMLU 67.31. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 3 15B Instruct Ft V2 AWQ by solidrust — VRAM 9.4GB, 8K context

Name: Llama 3 15B Instruct Ft V2 AWQ
Author: solidrust

Llama 3 15B Instruct Ft V2 AWQ is an open-source language model by solidrust. Features: 15b LLM, VRAM: 9.4GB, Context: 8K, Quantized, Instruction-Based, LLM Explorer Score: 0.14, Arc: 61.4, HellaSwag: 78.8, MMLU: 67.3, GSM8K: 72.5.

4-bit Autotrain compatible Awq Base model:elinas/llama-3-15b-... Base model:quantized:elinas/ll... Conversational Endpoints compatible Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/solidrust/Llama-3-15B-Instruct-ft-v2-AWQ

Llama 3 15B Instruct Ft V2 AWQ Parameters and Internals

Model Type

text-generation

Additional Notes

AWQ is a low-bit weight quantization method for faster Transformers-based inference with 4-bit quantization.

Input Output

Accepted Modalities:

text

LLM Name	Llama 3 15B Instruct Ft V2 AWQ
Repository 🤗	https://huggingface.co/solidrust/Llama-3-15B-Instruct-ft-v2-AWQ
Base Model(s)	Llama 3 15B Instruct Ft V2 elinas/Llama-3-15B-Instruct-ft-v2
Model Size	15b
Required VRAM	9.4 GB
Updated	2026-07-23
Maintainer	solidrust
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 4.4 GB: 2-of-2
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.41.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	float16

Rank the Llama 3 15B Instruct Ft V2 AWQ 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 15B Instruct Ft V2 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
L3 Aethora 15B V2 EXL2 6.0bpw	8K / 11.9 GB	6	1
L3 Aethora 15B V2 EXL2 8.0bpw	8K / 12.4 GB	4	1
L3 Aethora 15B V2 EXL2 4.0bpw	8K / 8.4 GB	2	1
L3 Aethora 15B V2 EXL2 5.0bpw	8K / 10.2 GB	0	1
Hamanasu 15B Instruct	16K / 29.4 GB	473	9
L3 Aethora 15B V2	8K / 30.1 GB	22	42
Meta Llama 3 15B Instruct	8K / 23.9 GB	3	1
OpenCrystal 15B L3 V3	8K / 30 GB	13	10
OpenCrystal L3 15B V2.1	8K / 30 GB	3	5
OpenCrystal 15B L3 V2	8K / 30 GB	3	6

Note: green Score (e.g. "73.2") means that the model is better than solidrust/Llama-3-15B-Instruct-ft-v2-AWQ.