What are the hardware requirements for OCC RAG 1.7B?

OCC RAG 1.7B requires approximately 3.4 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 OCC RAG 1.7B and how large is it?

OCC RAG 1.7B is developed by occ-ai, a model with 1.7b 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 OCC RAG 1.7B?

OCC RAG 1.7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OCC RAG 1.7B by occ-ai — VRAM 3.4GB, 32K context

Name: OCC RAG 1.7B
Author: occ-ai

OCC RAG 1.7B is an open-source language model by occ-ai. Features: 1.7b LLM, VRAM: 3.4GB, Context: 32K, License: mit, LLM Explorer Score: 0.31.

Arxiv:2606.00683 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-1.7b-bas... Conversational En Endpoints compatible Faithful-qa Occ Qwen3 Rag Region:us Ru Safetensors

Model Card on HF 🤗: https://huggingface.co/occ-ai/OCC-RAG-1.7B

OCC RAG 1.7B Benchmarks

LLME Score: 0.31391

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

OCC RAG 1.7B Parameters and Internals

LLM Name	OCC RAG 1.7B
Repository 🤗	https://huggingface.co/occ-ai/OCC-RAG-1.7B
Base Model(s)	Qwen/Qwen3-1.7B-Base Qwen/Qwen3-1.7B-Base
Model Size	1.7b
Required VRAM	3.4 GB
Updated	2026-06-07
Maintainer	occ-ai
Model Type	qwen3
Model Files	3.4 GB
Supported Languages	en ru
Model Architecture	Qwen3ForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	5.5.4
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Best Alternatives to OCC RAG 1.7B

Best Alternatives	Context / RAM	Downloads	Likes
Lucy 128K	128K / 3.4 GB	2730	109
Polaris 1.7B Preview	128K / 3.4 GB	41	8
DictaLM 3.0 1.7B Instruct	60K / 3.4 GB	1105	1
Qwen3 1.7B	40K / 4 GB	4405505	475
Supertron2 1.7B	40K / 3.4 GB	3046	7
Safety Model	40K / 3.4 GB	1100	0
15kDPO	40K / 3.4 GB	271	0
General Knowledge Model	40K / 3.4 GB	845	0
Math Model	40K / 3.4 GB	1001	0
...up Qwen3 1.7B Datav3 Only Mask	40K / 4.1 GB	2256	0

Note: green Score (e.g. "73.2") means that the model is better than occ-ai/OCC-RAG-1.7B.

Rank the OCC RAG 1.7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 54384 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

OCC RAG 1.7B by occ-ai

» All LLMs » occ-ai » OCC RAG 1.7B URL Share it on

OCC RAG 1.7B Benchmarks

OCC RAG 1.7B Parameters and Internals

Best Alternatives to OCC RAG 1.7B

Rank the OCC RAG 1.7B Capabilities

What open-source LLMs or SLMs are you in search of? 54384 in total.