What are the hardware requirements for Biggie SmoLlm 0.15B Base?

Biggie SmoLlm 0.15B Base requires approximately 0.2 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Biggie SmoLlm 0.15B Base and how large is it?

Biggie SmoLlm 0.15B Base is developed by nisten, a model with 0.15b 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 Biggie SmoLlm 0.15B Base?

Biggie SmoLlm 0.15B Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Biggie SmoLlm 0.15B Base by nisten — VRAM 0.2GB, 2K context

Name: Biggie SmoLlm 0.15B Base
Author: nisten

Biggie SmoLlm 0.15B Base is an open-source language model by nisten. Features: 0.15b LLM, VRAM: 0.2GB, Context: 2K, License: mit, Quantized, LLM Explorer Score: 0.17.

Base model:huggingfacetb/smoll... Base model:quantized:huggingfa... Dataset:ldjnr/capybara Deploy:azure Endpoints compatible Gguf Llama Pytorch Q8 Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base

Biggie SmoLlm 0.15B Base Parameters and Internals

Model Type

text generation

Additional Notes

The model is a cohesive merge, providing a powerful base for further training without the instruct component.

Training Details

Data Sources:

LDJnr/Capybara

Methodology:

Semi-automated continuous merging

Model Architecture:

Frankenstein merge of SmolLM components

Input Output

Input Format:

Natural language text prompting

Accepted Modalities:

text

Output Format:

Natural language text

Performance Tips:

Adjust temperature settings and min p for coherence.

LLM Name	Biggie SmoLlm 0.15B Base
Repository 🤗	https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base
Base Model(s)	SmolLM 135M HuggingFaceTB/SmolLM-135M
Model Size	0.15b
Required VRAM	0.2 GB
Updated	2026-07-10
Maintainer	nisten
Model Type	llama
Model Files	0.4 GB 0.2 GB 0.2 GB 0.3 GB
GGUF Quantization	Yes
Quantization Type	q8\|gguf
Model Architecture	LlamaForCausalLM
License	mit
Context Length	2048
Model Max Length	2048
Transformers Version	4.43.3
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49152
Torch Data Type	bfloat16

Rank the Biggie SmoLlm 0.15B Base 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 Biggie SmoLlm 0.15B Base

Best Alternatives	Context / RAM	Downloads	Likes
Fast R1 Small Experiment	2K / 0.3 GB	6	0
Qwq Finetune Result	2K / 0.3 GB	10	0