What are the hardware requirements for QuantumQuill?

QuantumQuill requires approximately 2.2 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed QuantumQuill and how large is it?

QuantumQuill is developed by Stefan171. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does QuantumQuill perform on standard benchmarks?

QuantumQuill has the following published scores: MMLU 23.2. Compare against reference models on this page or on the LLM Explorer leaderboards.

QuantumQuill by Stefan171 — VRAM 2.2GB, 16K context

Name: QuantumQuill
Author: Stefan171

QuantumQuill is an open-source language model by Stefan171. Features: LLM, VRAM: 2.2GB, Context: 16K, License: apache-2.0, Quantized, LLM Explorer Score: 0.17, Arc: 25.3, HellaSwag: 27.2, MMLU: 23.2.

4bit Autotrain compatible Base model:finetune:unsloth/ti... Base model:unsloth/tinyllama-b... Dataset:meta-math/metamathqa En Endpoints compatible Llama Pytorch Quantized Region:us Sft Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/Stefan171/QuantumQuill

QuantumQuill Parameters and Internals

Model Type

llama

Additional Notes

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

LLM Name	QuantumQuill
Repository 🤗	https://huggingface.co/Stefan171/QuantumQuill
Base Model(s)	Tinyllama Bnb 4bit unsloth/tinyllama-bnb-4bit
Required VRAM	2.2 GB
Updated	2025-09-23
Maintainer	Stefan171
Model Type	llama
Model Files	2.2 GB
Supported Languages	en
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.40.1
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the QuantumQuill 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 QuantumQuill

Best Alternatives	Context / RAM	Downloads	Likes
... Text Chat 512K 6.0bpw H6 EXL2	512K / 5.2 GB	6	1
... Text Chat 512K 5.0bpw H6 EXL2	512K / 4.4 GB	1	1
Slimorca Phi 3.5	128K / 7.6 GB	7	0
Phi 3.5 Instruct Vul	128K / 7.6 GB	17	0
... Text Chat 128K 6.0bpw H6 EXL2	128K / 5.2 GB	3	1
Unsloth Phi 4 4bit	16K / 8.3 GB	139	6
...ocalAI Functioncall Phi 4 V0.3	16K / 29.4 GB	91	10
...ocalAI Functioncall Phi 4 V0.3	16K / 29.4 GB	6	8
PARM V2 Phi 4 4K CoT PyTorch	16K / 29.4 GB	0	1
CodeMate V0.1 6.0bpw H6 EXL2	16K / 25.7 GB	1	1

Note: green Score (e.g. "73.2") means that the model is better than Stefan171/QuantumQuill.