What are the hardware requirements for Ibnsina 30B?

Ibnsina 30B requires approximately 1.1 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 Ibnsina 30B and how large is it?

Ibnsina 30B is developed by ibnsina-llm, a model with 30b 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 Ibnsina 30B?

Ibnsina 30B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ibnsina 30B by ibnsina-llm — VRAM 1.1GB, 32K context

Name: Ibnsina 30B
Author: ibnsina-llm

Ibnsina 30B is an open-source language model by ibnsina-llm. Features: 30b LLM, VRAM: 1.1GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.31.

Base-model Base model:quantized:qwen/qwen... Base model:qwen/qwen3-30b-a3b-... Continued-pretraining Conversational En Endpoints compatible Fa Farsi Gguf Ibnsina Llama.cpp Persian Q4 Quantized Qwen3 moe Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/ibnsina-llm/ibnsina-30b

Ibnsina 30B Parameters and Internals

LLM Name	Ibnsina 30B
Repository 🤗	https://huggingface.co/ibnsina-llm/ibnsina-30b
Base Model(s)	Qwen3 30B A3B Base Qwen/Qwen3-30B-A3B-Base
Model Size	30b
Required VRAM	1.1 GB
Updated	2026-09-19
Maintainer	ibnsina-llm
Model Type	qwen3_moe
Model Files	18.6 GB 32.5 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 1.1 GB
Supported Languages	fa en
GGUF Quantization	Yes
Quantization Type	q4\|gguf\|q4_k
Model Architecture	Qwen3MoeForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.51.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Ibnsina 30B 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 Ibnsina 30B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 30B A3B 128K GGUF	128K / 9 GB	2730	61
Qwen3 30B A3B GGUF	40K / 9 GB	54806	284
...en3 30B A3B Instruct 2507 4bit	256K / 17.2 GB	83766	12
...30B A3B Instruct 2507 MLX 4bit	256K / 17.2 GB	24652	8
...30B A3B Instruct 2507 MLX 8bit	256K / 32.5 GB	24655	3
...n3 Coder 30B A3B Instruct 4bit	256K / 17.2 GB	7252	33
Unslopper 30B A3B 6bit	256K / 24.7 GB	72	1
...r 30B A3B Instruct 4bit Dwq V2	256K / 17.2 GB	1342	10
...n3 Coder 30B A3B Instruct 8bit	256K / 32.5 GB	1277	7
...oder 30B A3B Instruct 4bit DWQ	256K / 17.2 GB	644	5