What are the hardware requirements for ChatMusician?

ChatMusician requires approximately 13.5 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed ChatMusician and how large is it?

ChatMusician is developed by m-a-p, a model with 6.7b 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 ChatMusician?

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

ChatMusician by m-a-p — VRAM 13.5GB, 2K context

Name: ChatMusician
Author: m-a-p

ChatMusician is an open-source language model by m-a-p. Features: 6.7b LLM, VRAM: 13.5GB, Context: 2K, License: mit, LLM Explorer Score: 0.11.

Arxiv:2402.16153 En Endpoints compatible Llama Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/m-a-p/ChatMusician

ChatMusician Parameters and Internals

Model Type

text-generation, music generation

Use Cases

Areas:

Research, Music composition

Applications:

Chore music creation, Melody harmonization, Musical form conditioned music generation

Primary Use Cases:

Music composition from chord progression, Text to music transformation

Limitations:

The model currently only supports strict format and close-ended instructions for music tasks., The model suffers from hallucinations., A large portion of the training data is stylized in Irish music style., Music understanding results reported are obtained in perplexity mode, direct generation may underperform.

Considerations:

Consider providing diverse and complex input data for better generalization.

Supported Languages

en (English)

Training Details

Data Sources:

MusicPile

Data Volume:

1.1M samples

Methodology:

Continual pre-training and finetuning on music scores and knowledge

Input Output

Input Format:

Text prompts with structured instructions

Accepted Modalities:

text

Output Format:

ABC notation

Performance Tips:

Using diverse and well-structured prompts can enhance output quality.

Release Notes

Version:

2024-2-28

Date:

2024-2-28

Notes:

Release of demo, code, model, data, and benchmark.

LLM Name	ChatMusician
Repository 🤗	https://huggingface.co/m-a-p/ChatMusician
Model Size	6.7b
Required VRAM	13.5 GB
Updated	2026-08-07
Maintainer	m-a-p
Model Type	llama
Model Files	10.0 GB: 1-of-2 3.5 GB: 2-of-2 10.0 GB: 1-of-2 3.5 GB: 2-of-2
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	mit
Context Length	2048
Model Max Length	2048
Transformers Version	4.32.0
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	32000
Torch Data Type	float16

Rank the ChatMusician 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 ChatMusician

Model	Likes	Downloads	VRAM
... ChatMusician Bnb 4bit Smashed	0	17	4 GB
ChatMusician GGUF	15	934	2 GB

Best Alternatives to ChatMusician

Best Alternatives	Context / RAM	Downloads	Likes
Gptnoise37	128K / 13.5 GB	67	0
...Deepseek Coder 6.7B Energy Sft	16K / 13.5 GB	261	0
Deepseek Coder 6.7B Base	16K / 13.5 GB	54216	124
Speechless Coder Ds 6.7B	16K / 13.5 GB	459	7
OpenCodeInterpreter DS 6.7B	16K / 13.5 GB	20040	135
...s Coder6.7b Reflct Adamw Iter2	16K / 13.5 GB	480	0
...ir8 Ds Coder6.7b Rmsprop Iter4	16K / 13.5 GB	183	0
...s Coder6.7b Reflct Adamw Iter1	16K / 13.5 GB	475	0
...ir8 Ds Coder6.7b Rmsprop Iter2	16K / 13.5 GB	183	0
...ir8 Ds Coder6.7b Rmsprop Iter3	16K / 13.5 GB	165	0

Note: green Score (e.g. "73.2") means that the model is better than m-a-p/ChatMusician.