What are the hardware requirements for Caigun Model 72B KGI?

Caigun Model 72B KGI requires approximately 144.6 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Caigun Model 72B KGI and how large is it?

Caigun Model 72B KGI is developed by APMIC, a model with 72b 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 Caigun Model 72B KGI?

Caigun Model 72B KGI is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Caigun Model 72B KGI by APMIC — VRAM 144.6GB, 32K context

Name: Caigun Model 72B KGI
Author: APMIC

Caigun Model 72B KGI is an open-source language model by APMIC. Features: 72b LLM, VRAM: 144.6GB, Context: 32K, LLM Explorer Score: 0.12.

Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/APMIC/caigun-model-72B-KGI

Caigun Model 72B KGI Parameters and Internals

LLM Name	Caigun Model 72B KGI
Repository 🤗	https://huggingface.co/APMIC/caigun-model-72B-KGI
Model Size	72b
Required VRAM	144.6 GB
Updated	2026-10-21
Maintainer	APMIC
Model Type	llama
Model Files	8.0 GB: 1-of-19 7.7 GB: 2-of-19 7.9 GB: 3-of-19 7.8 GB: 4-of-19 7.9 GB: 5-of-19 7.8 GB: 6-of-19 7.9 GB: 7-of-19 7.8 GB: 8-of-19 7.9 GB: 9-of-19 7.8 GB: 10-of-19 7.9 GB: 11-of-19 7.8 GB: 12-of-19 7.9 GB: 13-of-19 7.8 GB: 14-of-19 7.9 GB: 15-of-19 7.8 GB: 16-of-19 7.9 GB: 17-of-19 7.8 GB: 18-of-19 3.3 GB: 19-of-19
Model Architecture	LlamaForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.41.0.dev0
Tokenizer Class	GPT2Tokenizer
Padding Token	!
Vocabulary Size	152064
Torch Data Type	bfloat16

Rank the Caigun Model 72B KGI 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 Caigun Model 72B KGI

Best Alternatives	Context / RAM	Downloads	Likes
2 Pro Math	128K / 141.9 GB	10	0
TW3 JRGL V2	32K / 79.7 GB	16209	0
Le Triomphant ECE TW3	32K / 79.7 GB	16266	5
Smaug 72B V0.1	32K / 144.5 GB	8736	468
ECE TW3 JRGL V5	32K / 159.6 GB	8245	1
MoMo 72B Lora 1.8.7 DPO	32K / 208.5 GB	314	68
Rhea 72B V0.5	32K / 144.5 GB	8194	134
JuliusCesar 72B BeyonderV.0	32K / 74.2 GB	77	0
Rhea 125 V0.5	32K / 249 GB	13	1
Exodius 70B	32K / 144.6 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than APMIC/caigun-model-72B-KGI.