What are the hardware requirements for N Q 26M?

N Q 26M requires approximately 0.2 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 N Q 26M and how large is it?

N Q 26M is developed by q-project, a model with 26m 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 N Q 26M?

N Q 26M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

N Q 26M by q-project — VRAM 0.2GB, 4K context

Name: N Q 26M
Author: q-project

N Q 26M is an open-source language model by q-project. Features: 26m LLM, VRAM: 0.2GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.33.

Base-model Conversational Custom-architecture Custom code Dataset:deepvk/cultura ru edu Dataset:huggingfacefw/fineweb-... Dataset:wikimedia/wikipedia En Exact-circuits Gated-deltanet Linear-attention Nq4 Region:us Ru Russian Safetensors Tiny-model

Model Card on HF 🤗: https://huggingface.co/q-project/N-Q-26M

N Q 26M Parameters and Internals

LLM Name	N Q 26M
Repository 🤗	https://huggingface.co/q-project/N-Q-26M
Model Size	26m
Required VRAM	0.2 GB
Updated	2026-10-28
Maintainer	q-project
Model Type	nq4
Model Files	0.2 GB
Supported Languages	ru en
Model Architecture	NQ4ForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	5.17.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	8256

Rank the N Q 26M 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