What are the hardware requirements for Dhanishtha?

Dhanishtha requires approximately 3.5 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dhanishtha and how large is it?

Dhanishtha is developed by AI4free, a model with 1.5b 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 Dhanishtha?

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

Dhanishtha by AI4free — VRAM 3.5GB, 128K context

Name: Dhanishtha
Author: AI4free

Dhanishtha is an open-source language model by AI4free. Features: 1.5b LLM, VRAM: 3.5GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.17.

Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Conversational Dataset:abhaykoul/dhanishtha-r... Dataset:open-thoughts/openthou... En Endpoints compatible Gguf Quantized Qwen2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/HelpingAI/Dhanishtha

Dhanishtha Parameters and Internals

LLM Name	Dhanishtha
Repository 🤗	https://huggingface.co/HelpingAI/Dhanishtha
Base Model(s)	deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Model Size	1.5b
Required VRAM	3.5 GB
Updated	2026-09-20
Maintainer	AI4free
Model Type	qwen2
Model Files	3.6 GB 3.5 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.48.3
Tokenizer Class	LlamaTokenizer
Padding Token	<｜end▁of▁sentence｜>
Vocabulary Size	151936
Torch Data Type	float16

Rank the Dhanishtha 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 Dhanishtha

Best Alternatives	Context / RAM	Downloads	Likes
...Seek R1 Distill Qwen 1.5B GGUF	128K / 0.7 GB	58452	151
...Seek R1 Distill Qwen 1.5B GGUF	128K / 1.7 GB	134	6
ARIS Gold 1.5B	32K / 1 GB	222	1
Soulbox Cbt Therapy 1.5B	32K / 2.8 GB	110	0
Atem Wisdom 1.5B	32K / 1 GB	268	1
Qwen2.5 Coder Q4 K M C1	32K / 3.1 GB	48	0
Atem V1.1.5B	32K / 1 GB	126	0
WiNGPT Babel	32K / 1 GB	172	41
Qwen2 1.5B Instruct GGUF	32K / 0.7 GB	439	0
Qwen2 1.5B Instruct GGUF	32K / 0.7 GB	42	0

Note: green Score (e.g. "73.2") means that the model is better than HelpingAI/Dhanishtha.