What are the hardware requirements for Typhoon V1.5 72B Instruct?

Typhoon V1.5 72B Instruct requires approximately 144.5 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 Typhoon V1.5 72B Instruct and how large is it?

Typhoon V1.5 72B Instruct is developed by scb10x, 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 Typhoon V1.5 72B Instruct?

Typhoon V1.5 72B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Typhoon V1.5 72B Instruct by scb10x — VRAM 144.5GB, 32K context

Name: Typhoon V1.5 72B Instruct
Author: scb10x

Typhoon V1.5 72B Instruct is an open-source language model by scb10x. Features: 72b LLM, VRAM: 144.5GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.12.

Arxiv:2303.08774 Arxiv:2312.13951 Autotrain compatible Conversational En Endpoints compatible Instruct Qwen2 Region:us Safetensors Sharded Tensorflow Th

Model Card on HF 🤗: https://huggingface.co/scb10x/typhoon-v1.5-72b-instruct

Typhoon V1.5 72B Instruct Parameters and Internals

Model Type

text generation, instruct

Use Cases

Areas:

instructional, research

Limitations:

inaccurate outputs, bias

Considerations:

Developers should assess the risks associated with inaccuracies and biases.

Additional Notes

Still under development. Incorporates some level of guardrails.

Supported Languages

th (Thai), en (English)

Input Output

Input Format:

ChatML chat-template

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Do not load the model using 4-bit and 8-bit BNB as it may produce inaccurate results.

LLM Name	Typhoon V1.5 72B Instruct
Repository 🤗	https://huggingface.co/scb10x/typhoon-v1.5-72b-instruct
Model Size	72b
Required VRAM	144.5 GB
Updated	2025-09-23
Maintainer	scb10x
Model Type	qwen2
Instruction-Based	Yes
Model Files	4.8 GB: 1-of-30 5.0 GB: 2-of-30 5.0 GB: 3-of-30 4.8 GB: 4-of-30 4.8 GB: 5-of-30 4.8 GB: 6-of-30 5.0 GB: 7-of-30 5.0 GB: 8-of-30 4.8 GB: 9-of-30 4.8 GB: 10-of-30 4.8 GB: 11-of-30 5.0 GB: 12-of-30 5.0 GB: 13-of-30 4.8 GB: 14-of-30 4.8 GB: 15-of-30 4.8 GB: 16-of-30 5.0 GB: 17-of-30 5.0 GB: 18-of-30 4.8 GB: 19-of-30 4.8 GB: 20-of-30 4.8 GB: 21-of-30 5.0 GB: 22-of-30 5.0 GB: 23-of-30 4.8 GB: 24-of-30 4.8 GB: 25-of-30 4.8 GB: 26-of-30 5.0 GB: 27-of-30 5.0 GB: 28-of-30 4.8 GB: 29-of-30 2.9 GB: 30-of-30
Supported Languages	th en
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Typhoon V1.5 72B Instruct 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

Quantized Models of the Typhoon V1.5 72B Instruct

Model	Likes	Downloads	VRAM
Typhoon V1.5 72B Instruct AWQ	3	5	41 GB

Best Alternatives to Typhoon V1.5 72B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
EVA Qwen2.5 72B V0.2	128K / 146 GB	159	22
AceInstruct 72B	128K / 146 GB	88	18
...n2.5 72B 2x Instruct TIES V1.0	128K / 146.1 GB	81	1
...2B PT BR Instruct Experimental	128K / 146 GB	20	0
... BI Qwen2.5 72B PT BR Instruct	128K / 146 GB	5	0
...A Abliterated TIES Qwen2.5 72B	128K / 146.1 GB	8	1
72B Qwen2.5 Kunou V1	128K / 146 GB	77	26
EVA Qwen2.5 72B V0.1	128K / 146 GB	17	19
EVA Qwen2.5 72B V0.0	128K / 146 GB	10	5
Qwen2 72B Instruct	32K / 145.5 GB	61318	718

Note: green Score (e.g. "73.2") means that the model is better than scb10x/typhoon-v1.5-72b-instruct.