What are the hardware requirements for Codes 7B?

Codes 7B requires approximately 29.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codes 7B and how large is it?

Codes 7B is developed by seeklhy, 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 Codes 7B?

Codes 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Codes 7B by seeklhy — VRAM 29.4GB

Name: Codes 7B
Author: seeklhy

Codes 7B is an open-source language model by seeklhy. Features: 7b LLM, VRAM: 29.4GB, License: apache-2.0, Code Generating, LLM Explorer Score: 0.08.

Code Codegen Codegen Deploy:azure Endpoints compatible Gpt bigcode Pytorch Region:us Sharded Sql Sql Sql generation Text2sql

Model Card on HF 🤗: https://huggingface.co/seeklhy/codes-7b

Codes 7B Parameters and Internals

Model Type

SQL generation, Text-to-SQL

Training Details

Methodology:

Incrementally pre-trained on top of StarCoderBase-3B

Context Length:

8192

LLM Name	Codes 7B
Repository 🤗	https://huggingface.co/seeklhy/codes-7b
Model Size	7b
Required VRAM	29.4 GB
Updated	2026-07-27
Maintainer	seeklhy
Model Type	gpt_bigcode
Model Files	9.9 GB: 1-of-3 10.0 GB: 2-of-3 9.5 GB: 3-of-3
Supported Languages	code
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
License	apache-2.0
Transformers Version	4.32.0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49152
Torch Data Type	float32
Activation Function	gelu

Rank the Codes 7B 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 Codes 7B

Best Alternatives	Context / RAM	Downloads	Likes
Starcoder 7B Agent 0.3 Merged	0K / 14.7 GB	18	0
Starcoder 7B Agent 0.2 Merged	0K / 14.7 GB	11	0
Codes 7B Spider	0K / 29.4 GB	30	0
Codes 7B Merged	0K / 29.4 GB	8	0
Starcoderbase 7B	0K / 30.2 GB	10	1
Starcoderbase 7B	0K / 30.2 GB	9	1
Codes 7B Bird	0K / 29.4 GB	20	0
Codes 7B Bird With Evidence	0K / 29.4 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than seeklhy/codes-7b.