What are the hardware requirements for Stable Cypher Instruct 3B?

Stable Cypher Instruct 3B requires approximately 1.7 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Stable Cypher Instruct 3B and how large is it?

Stable Cypher Instruct 3B is developed by lakkeo, a model with 3b 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 Stable Cypher Instruct 3B?

Stable Cypher Instruct 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Stable Cypher Instruct 3B by lakkeo — VRAM 1.7GB, 16K context

Name: Stable Cypher Instruct 3B
Author: lakkeo

Stable Cypher Instruct 3B is an open-source language model by lakkeo. Features: 3b LLM, VRAM: 1.7GB, Context: 16K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.14.

8-bit Autotrain compatible Base model:finetune:stabilitya... Base model:stabilityai/stable-... Bitsandbytes Code Conversational Cypher En Gguf Graph Instruct Neo4j Quantized Region:us Safetensors Stablelm

Model Card on HF 🤗: https://huggingface.co/lakkeo/stable-cypher-instruct-3b

Stable Cypher Instruct 3B Parameters and Internals

Model Type

causal-lm, code, cypher, graph, neo4j

Additional Notes

The model is specialized in generating CYPHER queries from text for GraphDBs like neo4j. It demonstrates significant progress over previous state-of-the-art models like GPT4-o and is suggested to be finetuned on specific company syntax and entities.

Supported Languages

en (English)

Training Details

Data Sources:

https://github.com/neo4j-labs/text2cypher/tree/main/datasets/synthetic_opus_demodbs

Methodology:

Finetune

LLM Name	Stable Cypher Instruct 3B
Repository 🤗	https://huggingface.co/lakkeo/stable-cypher-instruct-3b
Base Model(s)	Stable Code Instruct 3B stabilityai/stable-code-instruct-3b
Model Size	3b
Required VRAM	1.7 GB
Updated	2025-06-12
Maintainer	lakkeo
Model Type	stablelm
Instruction-Based	Yes
Model Files	3.6 GB 1.7 GB 2.0 GB 3.0 GB 5.6 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	StableLmForCausalLM
License	apache-2.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.41.2
Tokenizer Class	GPTNeoXTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	50304
Torch Data Type	float32

Rank the Stable Cypher Instruct 3B 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 Stable Cypher Instruct 3B

Best Alternatives	Context / RAM	Downloads	Likes
Stable Cypher Instruct 3B	16K / 1.7 GB	864	34
Stable Code Instruct 3B	16K / 5.6 GB	2134	189
...struct 3B Spider 1500 Steps Q4	16K / 1.7 GB	36	0
Stable Code Instruct 3B 4bit	16K / 1.8 GB	52	5
...t 3B Mix Spider Bird 200 Steps	16K / 5.6 GB	9	0
... Instruct 3B Spider 3500 Steps	16K / 11.2 GB	5	0
Stable Code Instruct 3B AWQ	16K / 1.8 GB	6	0
Stablelm Zephyr 3B	4K / 5.6 GB	25834	261
ReMask 3B	4K / 11.2 GB	71	16

Note: green Score (e.g. "73.2") means that the model is better than lakkeo/stable-cypher-instruct-3b.