What are the hardware requirements for Qwen35 4B Sft V2?

Qwen35 4B Sft V2 requires approximately 9.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen35 4B Sft V2 and how large is it?

Qwen35 4B Sft V2 is developed by Sarim-Hash, 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 Qwen35 4B Sft V2?

Qwen35 4B Sft V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen35 4B Sft V2 by Sarim-Hash — VRAM 9.1GB

Name: Qwen35 4B Sft V2
Author: Sarim-Hash

Qwen35 4B Sft V2 is an open-source language model by Sarim-Hash. Features: 4b LLM, VRAM: 9.1GB, LLM Explorer Score: 0.28.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-4b Conversational Debate Endpoints compatible Full-finetune Image-text-to-text Qwen3 5 Region:us Safetensors Sft

Model Card on HF 🤗: https://huggingface.co/Sarim-Hash/qwen35-4b-sft-v2

Qwen35 4B Sft V2 Parameters and Internals

LLM Name	Qwen35 4B Sft V2
Repository 🤗	https://huggingface.co/Sarim-Hash/qwen35-4b-sft-v2
Base Model(s)	Qwen/Qwen3.5-4B Qwen/Qwen3.5-4B
Model Size	4b
Required VRAM	9.1 GB
Updated	2026-08-31
Maintainer	Sarim-Hash
Model Type	qwen3_5
Model Files	9.1 GB 0.0 GB
Model Architecture	Qwen3_5ForConditionalGeneration
Model Max Length	262144
Transformers Version	5.8.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen35 4B Sft V2 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 Qwen35 4B Sft V2

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
Fara1.5 4B	0K / 9.1 GB	4934	39
ASL 4B V1	0K / 9.3 GB	119	11
Qwen3.5 4B Finnish	0K / 9.1 GB	330	1
Qwen35 4b Sft VE	0K / 9.1 GB	3663	0
Qwen3.5 4B	0K / 9.3 GB	139961	26

Note: green Score (e.g. "73.2") means that the model is better than Sarim-Hash/qwen35-4b-sft-v2.