What are the hardware requirements for KeyLM 75M Instruct?

KeyLM 75M Instruct 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 KeyLM 75M Instruct and how large is it?

KeyLM 75M Instruct is developed by Eclipse-Senpai, a model with 75m 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 KeyLM 75M Instruct?

KeyLM 75M Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

KeyLM 75M Instruct by Eclipse-Senpai — VRAM 0.2GB, 2K context

Name: KeyLM 75M Instruct
Author: Eclipse-Senpai

KeyLM 75M Instruct is an open-source language model by Eclipse-Senpai. Features: 75m LLM, VRAM: 0.2GB, Context: 2K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.26.

Base model:finetune:minimalabs... Base model:minimalabs/keylm-75... Conversational Custom code Dataset:allenai/wildchat-1m Dataset:huggingfacefw/fineweb-... Dataset:huggingfacegeclm/reddi... Dataset:huggingfaceh4/ultracha... Dataset:huggingfacetb/cosmoped... Dataset:huggingfacetb/smol-smo... Dataset:huggingfacetb/smoltalk... Dataset:lmsys/lmsys-chat-1m Dataset:marin-community/stacke... Dataset:openassistant/oasst2 Dataset:wikimedia/wikipedia En Gqa Instruct Keylm Keylm75m Qk-norm Region:us Rope Safetensors Small-language-model Swiglu

Model Card on HF 🤗: https://huggingface.co/MinimaLabs/KeyLM-75M-Instruct

KeyLM 75M Instruct Parameters and Internals

LLM Name	KeyLM 75M Instruct
Repository 🤗	https://huggingface.co/MinimaLabs/KeyLM-75M-Instruct
Base Model(s)	KeyLM 75M Eclipse-Senpai/KeyLM-75M
Model Size	75m
Required VRAM	0.2 GB
Updated	2026-08-08
Maintainer	Eclipse-Senpai
Model Type	keylm75m
Instruction-Based	Yes
Model Files	0.2 GB
Supported Languages	en
Model Architecture	KeyLM75M
License	apache-2.0
Context Length	2048
Model Max Length	2048
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	12020
Torch Data Type	bfloat16

Rank the KeyLM 75M Instruct 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 KeyLM 75M Instruct

Best Alternatives	Context / RAM	Downloads	Likes
KeyLM 75M Instruct	2K / 0.2 GB	519	6

Note: green Score (e.g. "73.2") means that the model is better than MinimaLabs/KeyLM-75M-Instruct.