What are the hardware requirements for Astra Meal Parser?

Astra Meal Parser requires approximately 6.2 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Astra Meal Parser and how large is it?

Astra Meal Parser is developed by Turhan123, 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 Astra Meal Parser?

Astra Meal Parser is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Astra Meal Parser by Turhan123 — VRAM 6.2GB, 32K context

Name: Astra Meal Parser
Author: Turhan123

Astra Meal Parser is an open-source language model by Turhan123. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.24.

Arxiv:2106.09685 Arxiv:2412.15115 Base model:adapter:qwen/qwen2.... Base model:qwen/qwen2.5-3b-ins... Calorie-estimation Conversational En Endpoints compatible Instruct Json Lora Meal-parsing Nutrition Qwen2 Qwen2.5 Region:us Safetensors Sft Sharded Structured-output Tensorflow Tr Turkish Unsloth

Model Card on HF 🤗: https://huggingface.co/Turhan123/astra-meal-parser

Astra Meal Parser Parameters and Internals

LLM Name	Astra Meal Parser
Repository 🤗	https://huggingface.co/Turhan123/astra-meal-parser
Base Model(s)	Qwen/Qwen2.5-3B-Instruct Qwen/Qwen2.5-3B-Instruct
Model Size	3b
Required VRAM	6.2 GB
Updated	2026-07-19
Maintainer	Turhan123
Model Type	qwen2
Instruction-Based	Yes
Model Files	4.0 GB: 1-of-2 2.2 GB: 2-of-2
Supported Languages	tr en
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|PAD_TOKEN\|>
Vocabulary Size	151936
Torch Data Type	float16
Errors	replace

Rank the Astra Meal Parser 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 Astra Meal Parser

Best Alternatives	Context / RAM	Downloads	Likes
VibeThinker 3B	128K / 6.2 GB	52745	806
VibeThinker 3B	128K / 6.2 GB	361	0
Saba2 3B	128K / 6.2 GB	6	0
Tessa T1 3B	117K / 6.2 GB	10	5
UIGEN T1.5 3B	117K / 6.2 GB	7	1
Qwen2.5 3B Instruct	32K / 6.2 GB	5889234	545
Mahakal AI Fusion V3.0	32K / 6.2 GB	225	1
King AI Chat V3.0	32K / 6.2 GB	487	1
...Instruct Sheldon SFT V2 Merged	32K / 6.2 GB	216	0
...er 3B Instruct Spider Sft Grpo	32K / 6.2 GB	1025	1

Note: green Score (e.g. "73.2") means that the model is better than Turhan123/astra-meal-parser.