What are the hardware requirements for Qwen2.5 Vl 3B Food Extract Lora?

Qwen2.5 Vl 3B Food Extract Lora requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen2.5 Vl 3B Food Extract Lora and how large is it?

Qwen2.5 Vl 3B Food Extract Lora is developed by rukiyeberna, a model with 3b 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 Qwen2.5 Vl 3B Food Extract Lora?

Qwen2.5 Vl 3B Food Extract Lora is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen2.5 Vl 3B Food Extract Lora by rukiyeberna — VRAM 0.1GB

Name: Qwen2.5 Vl 3B Food Extract Lora
Author: rukiyeberna

Qwen2.5 Vl 3B Food Extract Lora is an open-source language model by rukiyeberna. Features: 3b LLM, VRAM: 0.1GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.25.

Adapter Base model:adapter:qwen/qwen2.... Base model:qwen/qwen2.5-vl-3b-... Conversational Dataset:mrdbourke/foodextract-... En Finetuned Food-extraction Image-text-to-text Instruct Json-generation Lora Multimodal Peft Qwen2 5 vl Region:us Safetensors Structured-outputs Vision Vision-language-model

Model Card on HF 🤗: https://huggingface.co/rukiyeberna/qwen2.5-vl-3b-food-extract-lora

Qwen2.5 Vl 3B Food Extract Lora Parameters and Internals

LLM Name	Qwen2.5 Vl 3B Food Extract Lora
Repository 🤗	https://huggingface.co/rukiyeberna/qwen2.5-vl-3b-food-extract-lora
Base Model(s)	Qwen/Qwen2.5-VL-3B-Instruct Qwen/Qwen2.5-VL-3B-Instruct
Model Size	3b
Required VRAM	0.1 GB
Updated	2026-09-05
Maintainer	rukiyeberna
Instruction-Based	Yes
Model Files	0.1 GB 0.1 GB
Supported Languages	en
Model Architecture	Adapter
License	apache-2.0
Model Max Length	131072
Is Biased	none
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	layers.13.mlp.gate_proj\|35.mlp.down_proj\|34.mlp.down_proj\|layers.9.mlp.gate_proj\|32.mlp.gate_proj\|layers.19.mlp.up_proj\|layers.26.mlp.up_proj\|32.mlp.down_proj\|layers.5.mlp.gate_proj\|layers.4.mlp.gate_proj\|layers.1.mlp.down_proj\|layers.2.mlp.gate_proj\|layers.16.mlp.down_proj\|layers.16.mlp.up_proj\|layers.24.mlp.up_proj\|layers.30.mlp.up_proj\|layers.21.mlp.down_proj\|layers.9.mlp.up_proj\|layers.13.mlp.down_proj\|layers.1.mlp.up_proj\|layers.30.mlp.gate_proj\|layers.0.mlp.down_proj\|layers.23.mlp.down_proj\|layers.11.mlp.gate_proj\|layers.2.mlp.down_proj\|layers.21.mlp.gate_proj\|layers.24.mlp.gate_proj\|35.mlp.gate_proj\|layers.17.mlp.up_proj\|layers.6.mlp.down_proj\|33.mlp.up_proj\|k_proj\|layers.7.mlp.up_proj\|layers.7.mlp.gate_proj\|layers.29.mlp.down_proj\|layers.22.mlp.up_proj\|layers.29.mlp.gate_proj\|layers.20.mlp.down_proj\|layers.18.mlp.gate_proj\|layers.25.mlp.up_proj\|layers.12.mlp.up_proj\|layers.3.mlp.up_proj\|layers.22.mlp.down_proj\|layers.8.mlp.gate_proj\|layers.23.mlp.up_proj\|layers.30.mlp.down_proj\|layers.25.mlp.gate_proj\|layers.2.mlp.up_proj\|layers.12.mlp.gate_proj\|layers.19.mlp.gate_proj\|layers.26.mlp.down_proj\|o_proj\|layers.9.mlp.down_proj\|layers.11.mlp.down_proj\|layers.4.mlp.up_proj\|layers.18.mlp.down_proj\|layers.3.mlp.gate_proj\|layers.29.mlp.up_proj\|layers.6.mlp.gate_proj\|layers.27.mlp.gate_proj\|layers.22.mlp.gate_proj\|layers.5.mlp.up_proj\|layers.3.mlp.down_proj\|layers.14.mlp.gate_proj\|layers.14.mlp.down_proj\|layers.24.mlp.down_proj\|35.mlp.up_proj\|layers.16.mlp.gate_proj\|layers.15.mlp.up_proj\|34.mlp.up_proj\|layers.23.mlp.gate_proj\|layers.20.mlp.up_proj\|layers.10.mlp.down_proj\|layers.7.mlp.down_proj\|layers.15.mlp.down_proj\|layers.28.mlp.gate_proj\|layers.25.mlp.down_proj\|layers.6.mlp.up_proj\|layers.18.mlp.up_proj\|layers.31.mlp.gate_proj\|layers.28.mlp.down_proj\|layers.10.mlp.up_proj\|layers.27.mlp.down_proj\|layers.11.mlp.up_proj\|layers.15.mlp.gate_proj\|layers.17.mlp.gate_proj\|layers.0.mlp.up_proj\|32.mlp.up_proj\|layers.1.mlp.gate_proj\|34.mlp.gate_proj\|layers.13.mlp.up_proj\|layers.8.mlp.down_proj\|v_proj\|layers.5.mlp.down_proj\|layers.14.mlp.up_proj\|layers.0.mlp.gate_proj\|q_proj\|layers.21.mlp.up_proj\|33.mlp.down_proj\|layers.31.mlp.up_proj\|layers.12.mlp.down_proj\|layers.8.mlp.up_proj\|layers.28.mlp.up_proj\|33.mlp.gate_proj\|layers.20.mlp.gate_proj\|layers.26.mlp.gate_proj\|layers.31.mlp.down_proj\|layers.4.mlp.down_proj\|layers.10.mlp.gate_proj\|layers.19.mlp.down_proj\|layers.17.mlp.down_proj\|layers.27.mlp.up_proj
LoRA Alpha	64
LoRA Dropout	0.05
R Param	32
Errors	replace

Rank the Qwen2.5 Vl 3B Food Extract Lora 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 Qwen2.5 Vl 3B Food Extract Lora

Best Alternatives	Context / RAM	Downloads	Likes
...wen2.5 VL 3B FakeBench LoRA V2	0K / 0.1 GB	17	2
Paperlens Qwen2.5 3B Qlora	0K / 0.1 GB	8	1
Qwen2.5 Coder 3B QLora	0K / 0.1 GB	15	1
AIBio LoRA	0K / 0.1 GB	28	1
StandardOne 3B LoRA	0K / 0.1 GB	42	1
...Agreement Qwen2.5 3B Grpo Lora	0K / 0 GB	12	0
... Checking Qwen2.5 3B Grpo Lora	0K / 0 GB	9	0
Qwen2.5 VL 3B FakeBench LoRA	0K / 0.1 GB	19	1
Talvion Support Sft Kb V2 Lora	0K / 0.1 GB	10	0
...2.5 3B Instruct Sheldon SFT V2	0K / 0.2 GB	9	1

Note: green Score (e.g. "73.2") means that the model is better than rukiyeberna/qwen2.5-vl-3b-food-extract-lora.