What are the hardware requirements for Lemer?

Lemer requires approximately 3.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Lemer and how large is it?

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

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

Name: Lemer
Author: lthn

Lemer is an open-source language model by lthn. Features: LLM, VRAM: 3.2GB, License: eupl-1.2, Quantized, LLM Explorer Score: 0.24.

LLM Name	Lemer
Repository 🤗	https://huggingface.co/lthn/lemer
Base Model(s)	LetheanNetwork/lemer LetheanNetwork/lemer
Required VRAM	3.2 GB
Updated	2026-07-19
Maintainer	lthn
Model Type	gemma4
Model Files	9.3 GB 3.2 GB 3.4 GB 3.6 GB 3.9 GB 5.0 GB
GGUF Quantization	Yes
Quantization Type	gguf\|q3\|q4_k\|q5_k
Model Architecture	Gemma4ForConditionalGeneration
License	eupl-1.2
Transformers Version	5.5.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

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	Context / RAM	Downloads	Likes
Gemma 4 E4B It GGUF	0K / 1 GB	510433	566
Gemma 4 E2B It GGUF	0K / 0.1 GB	496984	256
...s Reasoning GeminiCLI Mlx 4bit	0K / 11 GB	156680	31
OTel LLM E4B IT	0K / 31.5 GB	4677244	0
Sulphur Caption	0K / GB	47	4

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