What are the hardware requirements for Pretrained Qwen2.5 3B NCKH?

Pretrained Qwen2.5 3B NCKH requires approximately 6.8 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 Pretrained Qwen2.5 3B NCKH and how large is it?

Pretrained Qwen2.5 3B NCKH is developed by baesad, 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 Pretrained Qwen2.5 3B NCKH?

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

Pretrained Qwen2.5 3B NCKH by baesad — VRAM 6.8GB, 32K context

Name: Pretrained Qwen2.5 3B NCKH
Author: baesad

Pretrained Qwen2.5 3B NCKH is an open-source language model by baesad. Features: 3b LLM, VRAM: 6.8GB, Context: 32K, Quantized, LLM Explorer Score: 0.17.

Arxiv:1910.09700 Endpoints compatible Pytorch Qwen2 Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/baesad/Pretrained-Qwen2.5-3B-NCKH

Pretrained Qwen2.5 3B NCKH Parameters and Internals

LLM Name	Pretrained Qwen2.5 3B NCKH
Repository 🤗	https://huggingface.co/baesad/Pretrained-Qwen2.5-3B-NCKH
Model Size	3b
Required VRAM	6.8 GB
Updated	2026-08-07
Maintainer	baesad
Model Type	qwen2
Model Files	5.0 GB: 1-of-2 1.8 GB: 2-of-2 5.0 GB: 1-of-2 1.8 GB: 2-of-2
Quantization Type	4bit
Model Architecture	Qwen2ForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.51.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|vision_pad\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Pretrained Qwen2.5 3B NCKH 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 Pretrained Qwen2.5 3B NCKH

Best Alternatives	Context / RAM	Downloads	Likes
VibeThinker 3B	128K / 6.2 GB	52745	806
Ulam 1 Small	128K / 6.2 GB	202	4
VibeThinker 3B	128K / 6.2 GB	361	0
...ibeThinker 3B SFT Fable5 Glint	128K / 6.2 GB	65	0
Saba1.5 Pro 3B	128K / 5.8 GB	9	1
...b Sft Stage1.2 Ss1 Expert Math	128K / 15.1 GB	12	0
... Formattedtext Math Wiki Merge	128K / 15.1 GB	12	0
...2 Ss1 Expert Fictional Lyrical	128K / 15.1 GB	6	0
...tage1.1 Ss1 With Math.no Issue	128K / 15.1 GB	6	0
...ware Howto Formattedtext Merge	128K / 15.1 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than baesad/Pretrained-Qwen2.5-3B-NCKH.