What are the hardware requirements for Zeta Sft?

Zeta Sft requires approximately 1 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 Zeta Sft and how large is it?

Zeta Sft is developed by ryanskidmore, a model with 0.5b 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 Zeta Sft?

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

Zeta Sft by ryanskidmore — VRAM 1GB, 32K context

Name: Zeta Sft
Author: ryanskidmore

Zeta Sft is an open-source language model by ryanskidmore. Features: 0.5b LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, Code Generating, LLM Explorer Score: 0.18.

Autotrain compatible Base model:finetune:unsloth/qw... Base model:unsloth/qwen2.5-cod... Codegen En Endpoints compatible Qwen2 Region:us Safetensors Sft Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/ryanskidmore/zeta-sft

Zeta Sft Parameters and Internals

LLM Name	Zeta Sft
Repository 🤗	https://huggingface.co/ryanskidmore/zeta-sft
Base Model(s)	unsloth/Qwen2.5-Coder-0.5B unsloth/Qwen2.5-Coder-0.5B
Model Size	0.5b
Required VRAM	1 GB
Updated	2025-05-10
Maintainer	ryanskidmore
Model Type	qwen2
Model Files	1.0 GB
Supported Languages	en
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.51.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|PAD_TOKEN\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Zeta Sft 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 Zeta Sft

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 Coder 0.5B Instruct	32K / 1 GB	97439	74
Qwen2.5 Coder 0.5B	32K / 1 GB	32993	58
Qwen 2.5 Coder 0.5B SQL Writer	32K / 1 GB	13	0
Zeta 0.5B Sft	32K / 1 GB	8	0
...en2.5 Coder 0.5B FIM Spec Zeta	32K / 1.3 GB	6	0
Qw2 Ft Lc	32K / 2 GB	6	0
... 0.5B Finetune LeetcodeDataset	32K / 2 GB	6	0
Qwen CoMa 0.5B	32K / 1.3 GB	2	1
Qwen2.5 Coder 0.5B Instruct	32K / 1 GB	2321	5
Qwen2.5 Coder 0.5B Instruct	32K / 1 GB	14	0

Note: green Score (e.g. "73.2") means that the model is better than ryanskidmore/zeta-sft.