What are the hardware requirements for Qwen3.5 4B Browser Agent SFT FP8?

Qwen3.5 4B Browser Agent SFT FP8 requires approximately 5.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 4B Browser Agent SFT FP8 and how large is it?

Qwen3.5 4B Browser Agent SFT FP8 is developed by visnia-ai, a model with 4b 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 Qwen3.5 4B Browser Agent SFT FP8?

Qwen3.5 4B Browser Agent SFT FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 4B Browser Agent SFT FP8 by visnia-ai — VRAM 5.7GB

Name: Qwen3.5 4B Browser Agent SFT FP8
Author: visnia-ai

Qwen3.5 4B Browser Agent SFT FP8 is an open-source language model by visnia-ai. Features: 4b LLM, VRAM: 5.7GB, License: apache-2.0, LLM Explorer Score: 0.29.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-4b Browser-agent Conversational Endpoints compatible Fp8 Image-text-to-text Qwen3 5 Region:us Safetensors Sharded Tensorflow Tool-use Vllm Web-navigation

Model Card on HF 🤗: https://huggingface.co/visnia-ai/Qwen3.5-4B-Browser-Agent-SFT-FP8

Qwen3.5 4B Browser Agent SFT FP8 Parameters and Internals

LLM Name	Qwen3.5 4B Browser Agent SFT FP8
Repository 🤗	https://huggingface.co/visnia-ai/Qwen3.5-4B-Browser-Agent-SFT-FP8
Model Name	Qwen/Qwen3.5-4B
Base Model(s)	Qwen/Qwen3.5-4B Qwen/Qwen3.5-4B
Model Size	4b
Required VRAM	5.7 GB
Updated	2026-08-30
Maintainer	visnia-ai
Model Type	qwen3_5
Model Files	5.0 GB: 1-of-3 0.5 GB: 2-of-3 0.2 GB: 3-of-3
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.5 4B Browser Agent SFT FP8 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 Qwen3.5 4B Browser Agent SFT FP8

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 4B	0K / 9.3 GB	6575502	801
NuExtract3	0K / 0.2 GB	441570	324
Agents A1 4B	0K / 9.1 GB	177578	72
Qwen3.8 4B Distill	0K / 9.3 GB	1878	26
Qwen3.5 4B Base	0K / 9.3 GB	227814	79
ASL 4B V1	0K / 9.3 GB	119	11
Fara1.5 4B	0K / 9.1 GB	4934	39
Qwen35 4b Sft VE	0K / 9.1 GB	3663	0
AREX Turbo	0K / 9.1 GB	1071	45
Qwen3.5 4B	0K / 9.3 GB	139961	26

Note: green Score (e.g. "73.2") means that the model is better than visnia-ai/Qwen3.5-4B-Browser-Agent-SFT-FP8.