What are the hardware requirements for Ade Extract 3B V1?

Ade Extract 3B V1 requires approximately 1.7 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 Ade Extract 3B V1 and how large is it?

Ade Extract 3B V1 is developed by M37labsorg, 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 Ade Extract 3B V1?

Ade Extract 3B V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ade Extract 3B V1 by M37labsorg — VRAM 1.7GB, 32K context

Name: Ade Extract 3B V1
Author: M37labsorg

Ade Extract 3B V1 is an open-source language model by M37labsorg. Features: 3b LLM, VRAM: 1.7GB, Context: 32K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.3.

4-bit 4bit Base model:adapter:mlx-communi... Base model:mlx-community/qwen2... Conversational Endpoints compatible Gguf Instruct Lora Mlx Q4 Quantized Qwen2 Region:us Safetensors Slm-forge

Model Card on HF 🤗: https://huggingface.co/M37labsorg/ade-extract-3b-v1

Ade Extract 3B V1 Parameters and Internals

LLM Name	Ade Extract 3B V1
Repository 🤗	https://huggingface.co/M37labsorg/ade-extract-3b-v1
Base Model(s)	mlx-community/Qwen2.5-3B-Instruct-4bit mlx-community/Qwen2.5-3B-Instruct-4bit
Model Size	3b
Required VRAM	1.7 GB
Updated	2026-10-26
Maintainer	M37labsorg
Model Type	qwen2
Instruction-Based	Yes
Model Files	1.9 GB 3.3 GB 1.7 GB
GGUF Quantization	Yes
Quantization Type	q4\|4bit\|gguf\|q4_k
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.43.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
LoRA Model	Yes
Torch Data Type	bfloat16
Errors	replace

Rank the Ade Extract 3B V1 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 Ade Extract 3B V1

Best Alternatives	Context / RAM	Downloads	Likes
VibeThinker 3B Heretic	128K / 6.2 GB	1016	4
QwenDGAF Coder 3B	32K / 1.9 GB	1258	1
Boomslang	32K / 6.2 GB	722	1
LaboAI 0.4.0 3B	32K / 6.2 GB	150	1
Nexai V2	32K / 2.4 GB	72	1
TINY THINKER INSTRUCT	32K / 6.2 GB	1382	4
...n2.5 Coder 3B Instruct Heretic	32K / 6.2 GB	2410	1
Spyfood Brain V2	32K / 6.2 GB	153	0
Zenith 3B	32K / 6.3 GB	190	3
Coder GRPO 3B	32K / 6.2 GB	298	7

Note: green Score (e.g. "73.2") means that the model is better than M37labsorg/ade-extract-3b-v1.