What are the hardware requirements for OTel LLM 24B IT?

OTel LLM 24B IT requires approximately 95.3 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OTel LLM 24B IT and how large is it?

OTel LLM 24B IT is developed by att, a model with 24b 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 OTel LLM 24B IT?

OTel LLM 24B IT is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OTel LLM 24B IT by att — VRAM 95.3GB, 125K context

Name: OTel LLM 24B IT
Author: att

OTel LLM 24B IT is an open-source language model by att. Features: 24b LLM, VRAM: 95.3GB, Context: 125K, License: apache-2.0.

Base model:finetune:liquidai/l... Base model:liquidai/lfm2-24b-a... Conversational Dataset:farbodtavakkoli/otel-l... En Finetuned Full-parameter-fine-tuning Gsma Lfm2 moe Pytorch Rag Region:us Sharded Telecom Telecommunications

Model Card on HF 🤗: https://huggingface.co/att/OTel-LLM-24B-IT

OTel LLM 24B IT Parameters and Internals

LLM Name	OTel LLM 24B IT
Repository 🤗	https://huggingface.co/att/OTel-LLM-24B-IT
Base Model(s)	LFM2 24B A2B LiquidAI/LFM2-24B-A2B
Model Size	24b
Required VRAM	95.3 GB
Updated	2026-10-27
Maintainer	att
Model Type	lfm2_moe
Model Files	3.8 GB: 1-of-20 5.0 GB: 2-of-20 4.9 GB: 3-of-20 5.0 GB: 4-of-20 4.9 GB: 5-of-20 5.0 GB: 6-of-20 4.9 GB: 7-of-20 5.0 GB: 8-of-20 4.9 GB: 9-of-20 5.0 GB: 10-of-20 4.9 GB: 11-of-20 5.0 GB: 12-of-20 4.9 GB: 13-of-20 5.0 GB: 14-of-20 4.9 GB: 15-of-20 5.0 GB: 16-of-20 4.9 GB: 17-of-20 5.0 GB: 18-of-20 4.9 GB: 19-of-20 2.4 GB: 20-of-20
Supported Languages	en
Model Architecture	Lfm2MoeForCausalLM
License	apache-2.0
Context Length	128000
Model Max Length	128000
Transformers Version	5.3.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	65536

Rank the OTel LLM 24B IT 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 OTel LLM 24B IT

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 24B A2B	128K / 48.3 GB	9356	424
LFM2.5 24B A2B FP8	128K / 24.6 GB	1691	22
LFM2.5 24B A2B	128K / 48.3 GB	2243	8
LFM2.5 24B A2B Base	128K / 48.3 GB	362	35
LFM2.5 24B A2B ONNX	128K / GB	546	20
LFM2.5 24B A2B MLX Bf16	128K / 48.2 GB	1073	6
LFM2.5 24B A2B DERISKED BF16	128K / 48.3 GB	458	3
LFM2.5 24B A2B Preview Bf16	128K / 48.2 GB	596	1
LFM2.5 24B A2B NVFP4 W4A16	128K / 14.9 GB	239	1
LFM2.5 24B A2B NVFP4A16	128K / 0.3 GB	230	1

Note: green Score (e.g. "73.2") means that the model is better than att/OTel-LLM-24B-IT.