What are the hardware requirements for Starcoder2 15B Instruct V0.1?

Starcoder2 15B Instruct V0.1 requires approximately 53.4 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Starcoder2 15B Instruct V0.1 and how large is it?

Starcoder2 15B Instruct V0.1 is developed by mlx-community, a model with 15b 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 Starcoder2 15B Instruct V0.1?

Starcoder2 15B Instruct V0.1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Starcoder2 15B Instruct V0.1 by mlx-community — VRAM 53.4GB, 16K context

Name: Starcoder2 15B Instruct V0.1
Author: mlx-community

Starcoder2 15B Instruct V0.1 is an open-source language model by mlx-community. Features: 15b LLM, VRAM: 53.4GB, Context: 16K, License: bigcode-openrail-m, Instruction-Based, LLM Explorer Score: 0.12.

Base model:bigcode/starcoder2-... Base model:finetune:bigcode/st... Code Conversational Dataset:bigcode/self-oss-instr... Endpoints compatible Instruct Mlx Model-index Region:us Safetensors Sharded Starcoder2 Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/starcoder2-15b-instruct-v0.1

Starcoder2 15B Instruct V0.1 Parameters and Internals

Model Type

text generation

Additional Notes

This model was converted to MLX format using mlx-lm version **0.12.1**.

LLM Name	Starcoder2 15B Instruct V0.1
Repository 🤗	https://huggingface.co/mlx-community/starcoder2-15b-instruct-v0.1
Base Model(s)	Starcoder2 15B bigcode/starcoder2-15b
Model Size	15b
Required VRAM	53.4 GB
Updated	2026-08-04
Maintainer	mlx-community
Model Type	starcoder2
Instruction-Based	Yes
Model Files	5.3 GB: 1-of-2 5.3 GB: 1-of-4 5.3 GB: 1-of-7 5.3 GB: 2-of-4 5.4 GB: 2-of-7 4.4 GB: 3-of-4 5.4 GB: 3-of-7 1.1 GB: 4-of-4 5.3 GB: 4-of-7 5.1 GB: 5-of-7 4.9 GB: 6-of-7 0.6 GB: 7-of-7
Model Architecture	Starcoder2ForCausalLM
License	bigcode-openrail-m
Context Length	16384
Model Max Length	16384
Transformers Version	4.39.0.dev0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49152
Torch Data Type	bfloat16

Rank the Starcoder2 15B Instruct V0.1 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 Starcoder2 15B Instruct V0.1

Best Alternatives	Context / RAM	Downloads	Likes
Starcoder2 15B Instruct V0.1	16K / 31.9 GB	597	105
Dolphincoder Starcoder2 15B	16K / 31.9 GB	84	69
Dolphincoder Starcoder2 15B	16K / 31.9 GB	17	68
Starcoder2 15B Instruct	16K / 31.9 GB	6	7
...rCoder2 15B Instruct V0.1 GGUF	16K / 6.2 GB	412	0
...rCoder2 15B Instruct V0.1 GGUF	16K / 6.2 GB	261	0
Starcoder2 15B Instruct GPTQ	16K / 9.2 GB	2	2

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/starcoder2-15b-instruct-v0.1.