What are the hardware requirements for TinySphinx?

TinySphinx 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 TinySphinx and how large is it?

TinySphinx is developed by Daemontatox, 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 TinySphinx?

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

TinySphinx by Daemontatox — VRAM 1GB, 32K context

Name: TinySphinx
Author: Daemontatox

TinySphinx is an open-source language model by Daemontatox. Features: 0.5b LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.18.

4bit Autotrain compatible Conversational En Endpoints compatible Instruct Model-index Pytorch Quantized Qwen2 Region:us Safetensors Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/Daemontatox/TinySphinx

TinySphinx Parameters and Internals

LLM Name	TinySphinx
Repository 🤗	https://huggingface.co/Daemontatox/TinySphinx
Base Model(s)	unsloth/qwen2.5-0.5b-instruct-bnb-4bit unsloth/qwen2.5-0.5b-instruct-bnb-4bit
Model Size	0.5b
Required VRAM	1 GB
Updated	2025-01-06
Maintainer	Daemontatox
Model Type	qwen2
Instruction-Based	Yes
Model Files	1.0 GB 1.0 GB
Supported Languages	en
Quantization Type	4bit
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.47.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|PAD_TOKEN\|>
Vocabulary Size	151936
Torch Data Type	float16
Errors	replace

Rank the TinySphinx 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 TinySphinx

Best Alternatives	Context / RAM	Downloads	Likes
Pgabl Ft Nama Siswa	32K / 1 GB	253	0
Legal Rag Qwen Sft	32K / 1 GB	204	0
Atomight V2.2 UltraThink 0.5B	32K / 1 GB	54	1
...mmanuel Siagian Exp1 Lr2e5 R16	32K / 1 GB	11	0
BoyBarley Sparky	32K / 1 GB	17	0
...0.5B Instruct Unsloth Bnb 4bit	32K / 0.5 GB	34328	6
Qwen2.5 0.5B Instruct 4bit	32K / 0.3 GB	15769	7
Qwen2.5 0.5B Instruct Bnb 4bit	32K / 0.5 GB	14598	4
...5 Coder 0.5B Instruct Bnb 4bit	32K / 0.5 GB	6612	4
... Instruct Unsloth Merged 16bit	32K / 1.3 GB	25	2

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