What are the hardware requirements for OpenHathi 7B Hi V0.1 Base Gptq?

OpenHathi 7B Hi V0.1 Base Gptq requires approximately 4.2 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 OpenHathi 7B Hi V0.1 Base Gptq and how large is it?

OpenHathi 7B Hi V0.1 Base Gptq is developed by cmeraki, a model with 7b 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 OpenHathi 7B Hi V0.1 Base Gptq?

OpenHathi 7B Hi V0.1 Base Gptq is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OpenHathi 7B Hi V0.1 Base Gptq by cmeraki — VRAM 4.2GB, 4K context

Name: OpenHathi 7B Hi V0.1 Base Gptq
Author: cmeraki

OpenHathi 7B Hi V0.1 Base Gptq is an open-source language model by cmeraki. Features: 7b LLM, VRAM: 4.2GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.1.

4-bit Base model:meta-llama/llama-2-... Base model:quantized:meta-llam... En Gptq Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq

OpenHathi 7B Hi V0.1 Base Gptq Parameters and Internals

Model Type

llama

Additional Notes

Files are made using AutoGPTQ with a quantization configuration of 4 bits, group_size: 128, damp_percent: 0.1, desc_act: true. Max length is 1024. This is a base model not tuned for any instructions. Alpaca/Vicuna format works fine.

Supported Languages

Hindi (supported), English (supported)

Training Details

Data Sources:

https://huggingface.co/cmeraki/wiki_en_hi

Context Length:

1024

LLM Name	OpenHathi 7B Hi V0.1 Base Gptq
Repository 🤗	https://huggingface.co/cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq
Model Name	OpenHathi-7B-Hi-v0.1-Base-gptq
Model Creator	SarvamAI
Base Model(s)	Llama 2 7B Chat Hf meta-llama/Llama-2-7b-chat-hf
Model Size	7b
Required VRAM	4.2 GB
Updated	2026-06-06
Maintainer	cmeraki
Model Type	llama
Model Files	4.2 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.1
Tokenizer Class	LlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	48064
Torch Data Type	float16

Rank the OpenHathi 7B Hi V0.1 Base Gptq 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 OpenHathi 7B Hi V0.1 Base Gptq

Best Alternatives	Context / RAM	Downloads	Likes
Yarn Llama 2 7B 128K GPTQ	128K / 3.9 GB	8	7
Yarn Llama 2 7B 64K GPTQ	64K / 3.9 GB	10	1
... 7B 32K Instructions V4 Marlin	32K / 4.1 GB	8	0
Aixcoder 7B GPTQ	32K / 4.5 GB	4	1
Calm2 7B Chat GPTQ	32K / 4.4 GB	6	5
...Calm2 7B Chat GPTQ Calib Ja 1K	32K / 4.4 GB	4	5
Llama 2 7B 32K Instruct GPTQ	32K / 3.9 GB	49	27
Codebear 7B 4bit	16K / 3.9 GB	4	1
...a 7B Instruct GPTQ Calib Ja 1K	16K / 3.9 GB	6	0
Pandalyst 7B V1.2 GPTQ	16K / 3.9 GB	8	1

Note: green Score (e.g. "73.2") means that the model is better than cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq.