What are the hardware requirements for Kev 0.8B Merged?

Kev 0.8B Merged requires approximately 1.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Kev 0.8B Merged and how large is it?

Kev 0.8B Merged is developed by ayan4m1, a model with 0.8b 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 Kev 0.8B Merged?

Kev 0.8B Merged is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Kev 0.8B Merged by ayan4m1 — VRAM 1.8GB

Name: Kev 0.8B Merged
Author: ayan4m1

Kev 0.8B Merged is an open-source language model by ayan4m1. Features: 0.8b LLM, VRAM: 1.8GB, License: apache-2.0, LLM Explorer Score: 0.3.

8-bit Base model:jaredpalmer/kev-0.8... Base model:merge:jaredpalmer/k... Base model:merge:qwen/qwen3.5-... Base model:qwen/qwen3.5-0.8b-b... Conversational En Endpoints compatible Image-text-to-text Qwen3 5 Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/ayan4m1/kev-0.8b-merged

Kev 0.8B Merged Parameters and Internals

LLM Name	Kev 0.8B Merged
Repository 🤗	https://huggingface.co/ayan4m1/kev-0.8b-merged
Base Model(s)	Qwen/Qwen3.5-0.8B-Base jaredpalmer/kev-0.8b Qwen/Qwen3.5-0.8B-Base jaredpalmer/kev-0.8b
Model Size	0.8b
Required VRAM	1.8 GB
Updated	2026-10-03
Maintainer	ayan4m1
Model Type	qwen3_5
Model Files	0.8 GB 1.8 GB: 1-of-1
Supported Languages	en
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Tokenizer Class	TokenizersBackend
Padding Token	<\|vision_pad\|>
Errors	replace

Rank the Kev 0.8B Merged 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 Kev 0.8B Merged

Best Alternatives	Context / RAM	Downloads	Likes
OvisOCR2	0K / 1.7 GB	234670	480
Qwen3.5 0.8B	0K / 1.8 GB	2839884	655
Xiaomi OCR 0	0K / 1.8 GB	933	15
Qwen3.5 0.8B Base	0K / 1.8 GB	828054	92
Intern Decision 0.8B	0K / 0.2 GB	242	16
Tev1 0.8B Experimental	0K / 1.8 GB	644	9
OneJev 0.8B	0K / 2.2 GB	1101	2
PlayJev 0.8B	0K / 2.2 GB	353	2
Qwen3.5 0.8B	0K / 1.8 GB	47663	19
Jpt 0.8B	0K / 1.7 GB	151	2

Note: green Score (e.g. "73.2") means that the model is better than ayan4m1/kev-0.8b-merged.