What are the hardware requirements for Strela?

Strela requires approximately 6 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Strela and how large is it?

Strela is developed by gai-labs, 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 Strela?

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

Strela by gai-labs — VRAM 6GB, 4K context

Name: Strela
Author: gai-labs

Strela is an open-source language model by gai-labs. Features: 3b LLM, VRAM: 6GB, Context: 4K, License: cc-by-sa-4.0, LLM Explorer Score: 0.13.

En Endpoints compatible Llama Pytorch Region:us Ru Safetensors

Model Card on HF 🤗: https://huggingface.co/gai-labs/strela

Strela Parameters and Internals

Model Type

text generation

Use Cases

Areas:

dialog chatbot, story writing, song writing, bilingual translation

Primary Use Cases:

use on low-resource devices

Additional Notes

The model is optimized for performance on weaker devices.

Supported Languages

ru (full), en (full)

Input Output

Input Format:

text prompts

Accepted Modalities:

text

Output Format:

text

LLM Name	Strela
Repository 🤗	https://huggingface.co/gai-labs/strela
Model Size	3b
Required VRAM	6 GB
Updated	2026-04-17
Maintainer	gai-labs
Model Type	llama
Model Files	6.0 GB 6.0 GB
Supported Languages	ru en
Model Architecture	LlamaForCausalLM
License	cc-by-sa-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.33.2
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	49216
Torch Data Type	float16

Rank the Strela 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 Strela

Best Alternatives	Context / RAM	Downloads	Likes
Nanbeige4.1 3B	256K / 7.9 GB	20875	1161
Nanbeige4.1 3B Heretic	256K / 7.9 GB	149	50
Nanbeige4.1 3B Heretic Mxfp4	256K / 7.9 GB	34	2
Nanbeige4.1 3B Bf16	256K / 7.9 GB	47	3
...anbeige4.1 3B Heretic Bfloat16	256K / 7.9 GB	33	1
Nanbeige4.1 3B Heretic	256K / 7.9 GB	18	0
Nanbeige4.1 3B Heretic	256K / 7.9 GB	14	1
ISA 03 Mini 3B Hybrid Preview	256K / 6.5 GB	4	4
ToolMind Web 3B	192K / 7.9 GB	156	28
Llama 3.2 3B Instruct	128K / 6.5 GB	1829572	2368

Note: green Score (e.g. "73.2") means that the model is better than gai-labs/strela.