What are the hardware requirements for Ruadapt Qwen2.5 3B Ext U48 Instruct V4?

Ruadapt Qwen2.5 3B Ext U48 Instruct V4 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 Ruadapt Qwen2.5 3B Ext U48 Instruct V4 and how large is it?

Ruadapt Qwen2.5 3B Ext U48 Instruct V4 is developed by RefalMachine, 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 Ruadapt Qwen2.5 3B Ext U48 Instruct V4?

Ruadapt Qwen2.5 3B Ext U48 Instruct V4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ruadapt Qwen2.5 3B Ext U48 Instruct V4 by RefalMachine — VRAM 6.2GB, 32K context

Name: Ruadapt Qwen2.5 3B Ext U48 Instruct V4
Author: RefalMachine

Ruadapt Qwen2.5 3B Ext U48 Instruct V4 is an open-source language model by RefalMachine. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, Instruction-Based, LLM Explorer Score: 0.15.

Arxiv:2412.21140 Base model:finetune:refalmachi... Base model:refalmachine/ruadap... Conversational Dataset:dichspace/darulm Dataset:ilyagusev/saiga prefer... Dataset:ilyagusev/saiga scored Instruct Qwen2 Region:us Ru Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/RefalMachine/ruadapt_qwen2.5_3B_ext_u48_instruct_v4

Ruadapt Qwen2.5 3B Ext U48 Instruct V4 Parameters and Internals

LLM Name	Ruadapt Qwen2.5 3B Ext U48 Instruct V4
Repository 🤗	https://huggingface.co/RefalMachine/ruadapt_qwen2.5_3B_ext_u48_instruct_v4
Base Model(s)	RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256 RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256
Model Size	3b
Required VRAM	6.2 GB
Updated	2026-08-08
Maintainer	RefalMachine
Model Type	qwen2
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 1.2 GB: 2-of-2
Supported Languages	ru
Model Architecture	Qwen2ForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.45.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	147097
Torch Data Type	bfloat16
Errors	replace

Rank the Ruadapt Qwen2.5 3B Ext U48 Instruct V4 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 Ruadapt Qwen2.5 3B Ext U48 Instruct V4

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
...er 3B Instruct Spider Sft Grpo	32K / 6.2 GB	506	1
...2.5 3B Instruct SFT In WebShop	32K / 6.8 GB	347	1
SmallThinker 3B Preview	32K / 6.8 GB	30529	412
Qwen2.5 3B Haizi	32K / 6.2 GB	74	0

Note: green Score (e.g. "73.2") means that the model is better than RefalMachine/ruadapt_qwen2.5_3B_ext_u48_instruct_v4.