What are the hardware requirements for Tele FLM?

Tele FLM requires approximately 105.6 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 Tele FLM and how large is it?

Tele FLM is developed by CofeAI. 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 Tele FLM?

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

Tele FLM by CofeAI — VRAM 105.6GB, 4K context

Name: Tele FLM
Author: CofeAI

Tele FLM is an open-source language model by CofeAI. Features: LLM, VRAM: 105.6GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.16.

Arxiv:2404.16645 Custom code Feature-extraction Pytorch Region:us Sharded Teleflm

Model Card on HF 🤗: https://huggingface.co/CofeAI/Tele-FLM

Tele FLM Parameters and Internals

LLM Name	Tele FLM
Repository 🤗	https://huggingface.co/CofeAI/Tele-FLM
Required VRAM	105.6 GB
Updated	2026-08-12
Maintainer	CofeAI
Model Type	TeleFLM
Model Files	11.9 GB: 1-of-9 11.6 GB: 2-of-9 12.0 GB: 3-of-9 11.8 GB: 4-of-9 11.6 GB: 5-of-9 12.0 GB: 6-of-9 11.8 GB: 7-of-9 11.6 GB: 8-of-9 11.3 GB: 9-of-9
Model Architecture	TeleFLMModel\|TeleFLMForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.0
Tokenizer Class	TeleFLMTokenizer
Padding Token	<pad>
Vocabulary Size	80384
Torch Data Type	bfloat16

Rank the Tele FLM 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