What are the hardware requirements for AFM 4.5B Base Pre Anneal?

AFM 4.5B Base Pre Anneal requires approximately 18.5 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed AFM 4.5B Base Pre Anneal and how large is it?

AFM 4.5B Base Pre Anneal is developed by arcee-ai, a model with 4.5b 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 AFM 4.5B Base Pre Anneal?

AFM 4.5B Base Pre Anneal is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

AFM 4.5B Base Pre Anneal by arcee-ai — VRAM 18.5GB, 4K context

Name: AFM 4.5B Base Pre Anneal
Author: arcee-ai

AFM 4.5B Base Pre Anneal is an open-source language model by arcee-ai. Features: 4.5b LLM, VRAM: 18.5GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.18.

Arxiv:2410.06511 Ar Arcee De En Endpoints compatible Es Fr Hi It Ko Pt Region:us Ru Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/arcee-ai/AFM-4.5B-Base-Pre-Anneal

AFM 4.5B Base Pre Anneal Parameters and Internals

LLM Name	AFM 4.5B Base Pre Anneal
Repository 🤗	https://huggingface.co/arcee-ai/AFM-4.5B-Base-Pre-Anneal
Model Size	4.5b
Required VRAM	18.5 GB
Updated	2026-08-09
Maintainer	arcee-ai
Model Type	arcee
Model Files	1.8 GB: 1-of-10 1.9 GB: 2-of-10 2.0 GB: 3-of-10 2.0 GB: 4-of-10 2.0 GB: 5-of-10 2.0 GB: 6-of-10 2.0 GB: 7-of-10 2.0 GB: 8-of-10 1.5 GB: 9-of-10 1.3 GB: 10-of-10
Supported Languages	en es fr de it pt ru ar hi ko zh
Model Architecture	ArceeForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.53.2
Tokenizer Class	PreTrainedTokenizer
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the AFM 4.5B Base Pre Anneal 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 AFM 4.5B Base Pre Anneal

Best Alternatives	Context / RAM	Downloads	Likes
Austral 4.5B Winton	64K / 9.3 GB	90	12
AFM 4.5B Preview	64K / 9.3 GB	12	5

Note: green Score (e.g. "73.2") means that the model is better than arcee-ai/AFM-4.5B-Base-Pre-Anneal.