What are the hardware requirements for Fava Model?

Fava Model requires approximately 13.5 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Fava Model and how large is it?

Fava Model is developed by fava-uw, a model with 7b 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 Fava Model?

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

Fava Model by fava-uw — VRAM 13.5GB, 4K context

Name: Fava Model
Author: fava-uw

Fava Model is an open-source language model by fava-uw. Features: 7b LLM, VRAM: 13.5GB, Context: 4K, License: mit, LLM Explorer Score: 0.1.

Endpoints compatible Llama Pytorch Region:us Sharded Tensorboard

Model Card on HF 🤗: https://huggingface.co/fava-uw/fava-model

Fava Model Parameters and Internals

Model Type

verification

Additional Notes

The model is used for verifying texts against given evidence, identifying errors, and suggesting edits based on that evidence.

Input Output

Input Format:

Prompts with placeholders for evidence and output

Accepted Modalities:

text

Output Format:

Text output with identified errors and suggested edits

LLM Name	Fava Model
Repository 🤗	https://huggingface.co/fava-uw/fava-model
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-07-16
Maintainer	fava-uw
Model Type	llama
Model Files	10.0 GB: 1-of-2 3.5 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.32.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32001
Torch Data Type	bfloat16

Rank the Fava Model 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 Fava Model

Best Alternatives	Context / RAM	Downloads
124	1024K / 16.1 GB	93
162	1024K / 16.1 GB	60
157	1024K / 16.1 GB	101
118	1024K / 16.1 GB	15
A5.4	1024K / 16.1 GB	12
A3.4	1024K / 16.1 GB	13
A2.4	1024K / 16.1 GB	12
A6 L	1024K / 16.1 GB	201
M	1024K / 16.1 GB	127
2 Very Sci Fi	1024K / 16.1 GB	317

Note: green Score (e.g. "73.2") means that the model is better than fava-uw/fava-model.