What are the hardware requirements for Smaugredq?

Smaugredq requires approximately 4.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Smaugredq and how large is it?

Smaugredq is developed by Ammartatox, 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 Smaugredq?

Smaugredq is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Smaugredq by Ammartatox — VRAM 4.9GB

Name: Smaugredq
Author: Ammartatox

Smaugredq is an open-source language model by Ammartatox. Features: 8b LLM, VRAM: 4.9GB, License: apache-2.0, Quantized.

Base model:abacusai/llama-3-sm... En Endpoints compatible Gguf License:apache-2.0 Llama Quantized Region:us Unsloth

Model Card on HF 🤗: https://huggingface.co/Ammartatox/smaugredq

Smaugredq Parameters and Internals

LLM Name	Smaugredq
Repository 🤗	https://huggingface.co/Ammartatox/smaugredq
Base Model(s)	Llama 3 Smaug 8B abacusai/Llama-3-Smaug-8B
Model Size	8b
Required VRAM	4.9 GB
Updated	2024-07-04
Maintainer	Ammartatox
Model Type	llama
Model Files	16.1 GB 4.9 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	AutoModel
License	apache-2.0

Rank the Smaugredq 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 Smaugredq

Best Alternatives	Context / RAM	Downloads	Likes
...lama 3.1 8B Roleplay BSNL Gguf	0K / 4.9 GB	973	11
...ma 3.1 8B Roleplay Airtel Gguf	0K / 4.9 GB	658	8
Llama 3.1 8B Roleplay Jio Gguf	0K / 4.9 GB	123	5
Llama 3.1 8B Rp Tadashinu Gguf	0K / 4.9 GB	57	7
Llama 3.1 8B OneLastStory Gguf	0K / 4.9 GB	43	5
...B Instruct Bnb 4bit 24 1 100 1	0K / 16.1 GB	59	0
CleverBoi Llama 3.1 8B V2	0K / 16.1 GB	800	0
...leverBoi Llama 3.1 8B Instruct	0K / 0.2 GB	866	1
Meta Llama 3 8B Instruct GGUF	0K / 2 GB	96368	103
...ma 3 8B Instruct 32K V0.1 GGUF	0K / 2 GB	81087	59

Note: green Score (e.g. "73.2") means that the model is better than Ammartatox/smaugredq.