What are the hardware requirements for Quem 4B?

Quem 4B requires approximately 8 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Quem 4B and how large is it?

Quem 4B is developed by rodrigomt, a model with 4b 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 Quem 4B?

Quem 4B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Quem 4B by rodrigomt — VRAM 8GB, 40K context

Name: Quem 4B
Author: rodrigomt

Quem 4B is an open-source language model by rodrigomt. Features: 4b LLM, VRAM: 8GB, Context: 40K, Merged, LLM Explorer Score: 0.18.

Merged Model Base model:menlo/jan-nano Base model:polaris-project/pol... Base model:prithivmlmods/vulpe... Base model:tesslate/uigen-t3-4... Conversational En Menlo/jan-nano Polaris-project/polaris-4b-pre... Prithivmlmods/vulpecula-4b Pt Qwen3 Region:us Safetensors Sharded Tensorflow Tesslate/uigen-t3-4b-preview-m...

Model Card on HF 🤗: https://huggingface.co/rodrigomt/quem-4b

Quem 4B Parameters and Internals

LLM Name	Quem 4B
Repository 🤗	https://huggingface.co/rodrigomt/quem-4b
Base Model(s)	Jan Nano Vulpecula 4B Polaris 4B Preview UIGEN T3 4B Preview MAX Menlo/Jan-nano prithivMLmods/Vulpecula-4B POLARIS-Project/Polaris-4B-Preview Tesslate/UIGEN-T3-4B-Preview-MAX
Merged Model	Yes
Model Size	4b
Required VRAM	8 GB
Updated	2025-06-24
Maintainer	rodrigomt
Model Type	qwen3
Model Files	5.0 GB: 1-of-2 3.0 GB: 2-of-2
Supported Languages	en pt
Model Architecture	Qwen3ForCausalLM
Context Length	40960
Model Max Length	40960
Transformers Version	4.52.4
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|vision_pad\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Quem 4B 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 Quem 4B

Best Alternatives	Context / RAM	Downloads	Likes
FastContext 1.0 4B SFT	256K / 8.1 GB	5735	357
Qwen3 4B Instruct 2507	256K / 8.1 GB	3109972	911
GRPO 4 70	256K / 8.1 GB	14	0
...2.5 Flash Lite Preview Distill	256K / 8.1 GB	31	1
Lightning 4B	256K / 8.1 GB	13	6
Fable Traces	256K / 8.1 GB	385	210
Checkpoint 8000	256K / 8.1 GB	1453	0
Qwen3 4B Thinking 2507	256K / 8.1 GB	291023	606
FastContext 1.0 4B RL	256K / 8.1 GB	4559	61
Qwen3 4B Instruct 2507 FP8	256K / 5.2 GB	1100744	78

Note: green Score (e.g. "73.2") means that the model is better than rodrigomt/quem-4b.