What are the hardware requirements for RuadaptQwen2.5 32B Instruct?

RuadaptQwen2.5 32B Instruct requires approximately 65.7 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 RuadaptQwen2.5 32B Instruct and how large is it?

RuadaptQwen2.5 32B Instruct is developed by msu-rcc-lair, a model with 32b 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 RuadaptQwen2.5 32B Instruct?

RuadaptQwen2.5 32B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

RuadaptQwen2.5 32B Instruct by msu-rcc-lair — VRAM 65.7GB, 32K context

Name: RuadaptQwen2.5 32B Instruct
Author: msu-rcc-lair

RuadaptQwen2.5 32B Instruct is an open-source language model by msu-rcc-lair. Features: 32b LLM, VRAM: 65.7GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.17.

Arxiv:2412.21140 Conversational Dataset:dichspace/darulm Dataset:ilyagusev/saiga prefer... Dataset:ilyagusev/saiga scored Instruct Lora Qwen2 Region:us Ru Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/msu-rcc-lair/RuadaptQwen2.5-32B-instruct

RuadaptQwen2.5 32B Instruct Parameters and Internals

Model Type

text generation

Additional Notes

The model version is v1 and utilizes a unique tokenization method that significantly improves the generation speed for Russian text.

Supported Languages

ru (native)

Training Details

Data Sources:

ru-corpus

Methodology:

Continued pretraining with LEP

Model Architecture:

Qwen2.5 architecture with adapted tokenization

LLM Name	RuadaptQwen2.5 32B Instruct
Repository 🤗	https://huggingface.co/msu-rcc-lair/RuadaptQwen2.5-32B-instruct
Model Size	32b
Required VRAM	65.7 GB
Updated	2025-02-07
Maintainer	msu-rcc-lair
Model Type	qwen2
Instruction-Based	Yes
Model Files	4.8 GB: 1-of-14 4.9 GB: 2-of-14 4.9 GB: 3-of-14 4.9 GB: 4-of-14 4.9 GB: 5-of-14 4.9 GB: 6-of-14 4.9 GB: 7-of-14 4.9 GB: 8-of-14 4.9 GB: 9-of-14 4.9 GB: 10-of-14 4.9 GB: 11-of-14 4.9 GB: 12-of-14 4.9 GB: 13-of-14 2.1 GB: 14-of-14
Supported Languages	ru
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.45.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	147200
LoRA Model	Yes
Torch Data Type	bfloat16
Errors	replace

Rank the RuadaptQwen2.5 32B Instruct 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 RuadaptQwen2.5 32B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
...y Qwen2.5coder 32B V24.1q 200K	195K / 65.8 GB	9	2
...wen2.5 32B Inst BaseMerge TIES	128K / 65.8 GB	28	17
...wen2.5 32B Inst BaseMerge TIES	128K / 65.8 GB	22	4
Franqwenstein 35B	128K / 69.8 GB	5	8
ELYZA Thinking 1.0 Qwen 32B	128K / 65.8 GB	23	10
Archaeo 32B KTO	128K / 65.8 GB	19	4
Hamanasu Magnum QwQ 32B	128K / 65.8 GB	295	9
Qwen2.5 32B Gokgok Step3	128K / 65.7 GB	6	0
Openthaigpt R1 32B Instruct	128K / 65.8 GB	33	8
Qwen2.5 32B Dark Days Stage2	128K / 65.8 GB	9	0

Note: green Score (e.g. "73.2") means that the model is better than msu-rcc-lair/RuadaptQwen2.5-32B-instruct.