What are the hardware requirements for Olmo Compassion Part1?

Olmo Compassion Part1 requires approximately 14.5 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Olmo Compassion Part1 and how large is it?

Olmo Compassion Part1 is developed by somaxsoma, a model with 7.3b 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 Olmo Compassion Part1?

Olmo Compassion Part1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Olmo Compassion Part1 by somaxsoma — VRAM 14.5GB, 64K context

Name: Olmo Compassion Part1
Author: somaxsoma

Olmo Compassion Part1 is an open-source language model by somaxsoma. Features: 7.3b LLM, VRAM: 14.5GB, Context: 64K, License: apache-2.0, Merged, LLM Explorer Score: 0.29.

Merged Model Base model:compassioninmachine... Base model:finetune:compassion... Conversational En Endpoints compatible Olmo3 Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/somaxsoma/olmo-compassion-part1

Olmo Compassion Part1 Parameters and Internals

LLM Name	Olmo Compassion Part1
Repository 🤗	https://huggingface.co/somaxsoma/olmo-compassion-part1
Base Model(s)	CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-4 CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-4
Merged Model	Yes
Model Size	7.3b
Required VRAM	14.5 GB
Updated	2026-10-10
Maintainer	somaxsoma
Model Type	olmo3
Model Files	1.9 GB: 1-of-8 1.9 GB: 2-of-8 1.9 GB: 3-of-8 1.9 GB: 4-of-8 2.0 GB: 5-of-8 2.0 GB: 6-of-8 2.0 GB: 7-of-8 0.9 GB: 8-of-8
Supported Languages	en
Model Architecture	Olmo3ForCausalLM
License	apache-2.0
Context Length	65536
Model Max Length	65536
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100278
Torch Data Type	bfloat16

Rank the Olmo Compassion Part1 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 Olmo Compassion Part1

Best Alternatives	Context / RAM	Downloads	Likes
BITD Baseline	64K / 29.3 GB	45	0