What are the hardware requirements for Llama 3 8B Instruct Coder AWQ?

Llama 3 8B Instruct Coder AWQ requires approximately 5.8 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 8B Instruct Coder AWQ and how large is it?

Llama 3 8B Instruct Coder AWQ is developed by solidrust, a model with 8b 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 Llama 3 8B Instruct Coder AWQ?

Llama 3 8B Instruct Coder AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 3 8B Instruct Coder AWQ by solidrust — VRAM 5.8GB, 8K context

Name: Llama 3 8B Instruct Coder AWQ
Rating: 3 (1 reviews)
Author: solidrust

Llama 3 8B Instruct Coder AWQ is an open-source language model by solidrust. Features: 8b LLM, VRAM: 5.8GB, Context: 8K, License: apache-2.0, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.12.

4-bit Autotrain compatible Awq Base model:quantized:rombodawg... Base model:rombodawg/llama-3-8... Codegen Conversational En Endpoints compatible Instruct Llama Quantized Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/solidrust/Llama-3-8B-Instruct-Coder-AWQ

Llama 3 8B Instruct Coder AWQ Parameters and Internals

Model Type

4-bit, AWQ, text-generation, autotrain_compatible, endpoints_compatible, text-generation-inference, transformers, unsloth, llama, trl, sft

Additional Notes

Model supports AWQ, which is a 4-bit quantization method enhancing performance compared to previous quantization techniques.

Training Details

Data Volume:

65k Codefeedback dataset + 150k Code Feedback Filtered Instruction dataset

Methodology:

Uses 'Qalore' method with Qlora and Galore techniques

Training Time:

130 hours

Hardware Used:

RTX A4000 16GB

LLM Name	Llama 3 8B Instruct Coder AWQ
Repository 🤗	https://huggingface.co/solidrust/Llama-3-8B-Instruct-Coder-AWQ
Base Model(s)	Llama 3 8B Instruct Coder rombodawg/Llama-3-8B-Instruct-Coder
Model Size	8b
Required VRAM	5.8 GB
Updated	2026-07-29
Maintainer	solidrust
Model Type	llama
Instruction-Based	Yes
Model Files	4.7 GB: 1-of-2 1.1 GB: 2-of-2
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	float16

Rank the Llama 3 8B Instruct Coder 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 8B Instruct Coder AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...r 8B Instruct Unsloth Bnb 4bit	32K / 6.5 GB	67	1
...eed Coder 8B Instruct Bnb 4bit	32K / 6.1 GB	4	2
Test Dataset Codellama 3 8B	8K / 16.1 GB	14	78
Seed Coder 8B Instruct	32K / 16.5 GB	2894	117
Seed Coder 8B Instruct GGUF	32K / 2.3 GB	1718	12
Seed Coder 8B Instruct V1	32K / 32.9 GB	43	2
Seed Coder 8B Instruct	32K / 16.5 GB	25	1
Wasm Coder 8B Instruct V1	32K / 32.9 GB	5	3
Athena Llama Coder 3 8B	32K / 16.1 GB	15	1
...plete Coder Instruct 8B Merged	8K / 16.1 GB	7703	2

Note: green Score (e.g. "73.2") means that the model is better than solidrust/Llama-3-8B-Instruct-Coder-AWQ.