What are the hardware requirements for Szl Receiptagent Qwen35 0.8B V3?

Szl Receiptagent Qwen35 0.8B V3 requires approximately 3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Szl Receiptagent Qwen35 0.8B V3 and how large is it?

Szl Receiptagent Qwen35 0.8B V3 is developed by SZLHOLDINGS, 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 Szl Receiptagent Qwen35 0.8B V3?

Szl Receiptagent Qwen35 0.8B V3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Szl Receiptagent Qwen35 0.8B V3 by SZLHOLDINGS — VRAM 3GB

Name: Szl Receiptagent Qwen35 0.8B V3
Author: SZLHOLDINGS

Szl Receiptagent Qwen35 0.8B V3 is an open-source language model by SZLHOLDINGS. Features: 0.8b LLM, VRAM: 3GB, License: apache-2.0.

Adapter Base model:adapter:qwen/qwen3.... Base model:qwen/qwen3.5-0.8b Conversational Dataset:szlholdings/governed-a... Dataset:szlholdings/governed-r... Dataset:szlholdings/receipted-... Dataset:szlholdings/szl-traini... Doctrine-v11 En Finetuned Governed-ai Lora Peft Proposal-only Qwen3.5 Qwen3 5 text Receipt-agent Region:us Safetensors Szl-holdings Unsloth

Model Card on HF 🤗: https://huggingface.co/SZLHOLDINGS/szl-receiptagent-qwen35-0.8b-v3

Szl Receiptagent Qwen35 0.8B V3 Parameters and Internals

LLM Name	Szl Receiptagent Qwen35 0.8B V3
Repository 🤗	https://huggingface.co/SZLHOLDINGS/szl-receiptagent-qwen35-0.8b-v3
Base Model(s)	Qwen/Qwen3.5-0.8B Qwen/Qwen3.5-0.8B
Model Size	0.8b
Required VRAM	3 GB
Updated	2026-11-06
Maintainer	SZLHOLDINGS
Model Files	0.0 GB 3.0 GB
Supported Languages	en
Model Architecture	Adapter
License	apache-2.0
Model Max Length	262144
Is Biased	none
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	(\|?\|:\|.\|\|?\|(\|?\|:\|l\|a\|n\|g\|u\|a\|g\|e\|\|\|t\|e\|x\|t\|)\|.\|\|?\|(\|?\|:\|s\|e\|l\|f\|_\|a\|t\|t\|n\|\|\|a\|t\|t\|e\|n\|t\|i\|o\|n\|\|\|a\|t\|t\|n\|\|\|m\|i\|x\|e\|r\|\|\|m\|l\|p\|\|\|f\|e\|e\|d\|_\|f\|o\|r\|w\|a\|r\|d\|\|\|f\|f\|n\|\|\|d\|e\|n\|s\|e\|\|\|m\|i\|x\|e\|r\|)\|.\|*\|?\|(\|?\|:\|q\|_\|p\|r\|o\|j\|\|\|k\|_\|p\|r\|o\|j\|\|\|v\|_\|p\|r\|o\|j\|\|\|o\|_\|p\|r\|o\|j\|\|\|g\|a\|t\|e\|_\|p\|r\|o\|j\|\|\|u\|p\|_\|p\|r\|o\|j\|\|\|d\|o\|w\|n\|_\|p\|r\|o\|j\|)\|)\|\|\|(\|?\|:\|\\|b\|m\|o\|d\|e\|l\|\\|.\|l\|a\|y\|e\|r\|s\|\\|.\|[\|\\|d\|]\|{\|1\|,\|}\|\\|.\|(\|?\|:\|s\|e\|l\|f\|_\|a\|t\|t\|n\|\|\|a\|t\|t\|e\|n\|t\|i\|o\|n\|\|\|a\|t\|t\|n\|\|\|m\|i\|x\|e\|r\|\|\|m\|l\|p\|\|\|f\|e\|e\|d\|_\|f\|o\|r\|w\|a\|r\|d\|\|\|f\|f\|n\|\|\|d\|e\|n\|s\|e\|\|\|m\|i\|x\|e\|r\|)\|\\|.\|(\|?\|:\|(\|?\|:\|q\|_\|p\|r\|o\|j\|\|\|k\|_\|p\|r\|o\|j\|\|\|v\|_\|p\|r\|o\|j\|\|\|o\|_\|p\|r\|o\|j\|\|\|g\|a\|t\|e\|_\|p\|r\|o\|j\|\|\|u\|p\|_\|p\|r\|o\|j\|\|\|d\|o\|w\|n\|_\|p\|r\|o\|j\|)\|)\|)
LoRA Alpha	32
LoRA Dropout	0
R Param	16
Errors	replace

Rank the Szl Receiptagent Qwen35 0.8B V3 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 Szl Receiptagent Qwen35 0.8B V3

Best Alternatives	Context / RAM	Downloads	Likes
Kev 0.8B	0K / 0 GB	12153	39
Qwen3.5 0.8B Decision	0K / 1.8 GB	485	5
Decision 0.8B	0K / 0 GB	19	1
... Jev Budget20 Qwen35 0.8B Lora	0K / 0 GB	64	1
Payo 0.8B Core Preview	0K / 0.1 GB	18	1
Mc Ai	0K / 0 GB	23	1
Connect C1 0.8B V0.1	0K / 0 GB	0	1
...wen3.5 0.8B CommonsenseQA LoRA	0K / 0 GB	9	1
...zl Receiptagent Qwen35 0.8B V2	0K / 0 GB	290	1
Khipu R3	0K / 3 GB	54	0

Note: green Score (e.g. "73.2") means that the model is better than SZLHOLDINGS/szl-receiptagent-qwen35-0.8b-v3.