What are the hardware requirements for Nawah 50M RAG Support 2K?

Nawah 50M RAG Support 2K requires approximately 0.1 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nawah 50M RAG Support 2K and how large is it?

Nawah 50M RAG Support 2K is developed by oddadmix, a model with 50m 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 Nawah 50M RAG Support 2K?

Nawah 50M RAG Support 2K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nawah 50M RAG Support 2K by oddadmix — VRAM 0.1GB, 2K context

Name: Nawah 50M RAG Support 2K
Author: oddadmix

Nawah 50M RAG Support 2K is an open-source language model by oddadmix. Features: 50m LLM, VRAM: 0.1GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.33.

Ar Arabic Base model:oddadmix/50m-2048-e... Base model:quantized:oddadmix/... Conversational Customer-support Dataset:oddadmix/arabic-rag-ch... Dataset:oddadmix/arabic-rag-ch... Dataset:oddadmix/arabic-rag-su... Endpoints compatible Gguf Grounded-qa Grpo Llama Llama.cpp Msa Rag Region:us Safetensors Small-language-model

Model Card on HF 🤗: https://huggingface.co/oddadmix/Nawah-50M-RAG-Support-2K

Nawah 50M RAG Support 2K Parameters and Internals

LLM Name	Nawah 50M RAG Support 2K
Repository 🤗	https://huggingface.co/oddadmix/Nawah-50M-RAG-Support-2K
Base Model(s)	50M 2048 Emhotob oddadmix/50M-2048-Emhotob
Model Size	50m
Required VRAM	0.1 GB
Updated	2026-08-21
Maintainer	oddadmix
Model Type	llama
Model Files	0.1 GB 0.0 GB
Supported Languages	ar
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	5.12.1
Tokenizer Class	TokenizersBackend
Padding Token	<pad>
Vocabulary Size	32002

Rank the Nawah 50M RAG Support 2K 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 Nawah 50M RAG Support 2K

Best Alternatives	Context / RAM	Downloads	Likes
Nyun C2 Llama3 50B	8K / 100.8 GB	8	11
Supra Router 51M	5K / 0.1 GB	2299	129
Supra 1.5 50M Instruct Exp	5K / 0.1 GB	2307	49
Supra1.5 50M Instruct Exp	5K / 0.1 GB	2023	49
Supra 1.5 50M Base Exp	5K / 0.2 GB	1738	18
Supra Title 50M Pre	5K / 0.1 GB	248	8
Tashkeel 50M	2K / 0.1 GB	249	1
50M 2048 Emhotob	2K / 0.2 GB	741	3
Quark 50M Instruct	2K / 0.1 GB	946	2
Quark 50M V2	2K / 0.1 GB	333	6

Note: green Score (e.g. "73.2") means that the model is better than oddadmix/Nawah-50M-RAG-Support-2K.