What are the hardware requirements for D7?

D7 requires approximately 5.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed D7 and how large is it?

D7 is developed by stojchet, a model with 1.3b 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 D7?

D7 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

D7 by stojchet — VRAM 5.4GB

Name: D7
Author: stojchet

D7 is an open-source language model by stojchet. Features: 1.3b LLM, VRAM: 5.4GB, Code Generating, LLM Explorer Score: 0.13.

Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Codegen Dataset:generator Dpo Endpoints compatible Generated from trainer Llama Lora Region:us Safetensors Sharded Tensorflow Trl

Model Card on HF 🤗: https://huggingface.co/stojchet/d7

D7 Parameters and Internals

Training Details

Data Sources:

generator

LLM Name	D7
Repository 🤗	https://huggingface.co/stojchet/d7
Base Model(s)	deepseek-ai/deepseek-coder-1.3b-base deepseek-ai/deepseek-coder-1.3b-base
Model Size	1.3b
Required VRAM	5.4 GB
Updated	2026-07-31
Maintainer	stojchet
Model Files	5.0 GB: 1-of-2 0.4 GB: 2-of-2 0.0 GB
Supported Languages	python
Generates Code	Yes
Model Architecture	AutoModelForCausalLM
Model Max Length	16384
Tokenizer Class	LlamaTokenizer
Padding Token	<｜end▁of▁sentence｜>
LoRA Model	Yes
LoRA Alpha	16
LoRA Dropout	0.15

Rank the D7 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 D7

Best Alternatives	Context / RAM	Downloads
Kto5k1	16K / 5.4 GB	16
Dpo7	0K / 5.4 GB	11
Dpo6	0K / 5.4 GB	10
Dpo1	0K / 5.4 GB	9
Dpo5	0K / 5.4 GB	8
Jd2	0K / 5.4 GB	7
K6	0K / 5.4 GB	7
K5	0K / 5.4 GB	5
Jd3	0K / 5.4 GB	5
Nkto4	0K / 5.4 GB	10

Note: green Score (e.g. "73.2") means that the model is better than stojchet/d7.