What are the hardware requirements for HuggingFaceH4 Starchat2 15B V0.1 4bits?

HuggingFaceH4 Starchat2 15B V0.1 4bits requires approximately 9.9 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 HuggingFaceH4 Starchat2 15B V0.1 4bits and how large is it?

HuggingFaceH4 Starchat2 15B V0.1 4bits is developed by RichardErkhov, 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 HuggingFaceH4 Starchat2 15B V0.1 4bits?

HuggingFaceH4 Starchat2 15B V0.1 4bits is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

HuggingFaceH4 Starchat2 15B V0.1 4bits by RichardErkhov — VRAM 9.9GB, 16K context

Name: HuggingFaceH4 Starchat2 15B V0.1 4bits
Author: RichardErkhov

HuggingFaceH4 Starchat2 15B V0.1 4bits is an open-source language model by RichardErkhov. Features: 15b LLM, VRAM: 9.9GB, Context: 16K, LLM Explorer Score: 0.12.

Arxiv:2311.07911 Arxiv:2402.19173 4-bit Alignment-handbook Bitsandbytes Conversational Endpoints compatible Generated from trainer Region:us Safetensors Sharded Starcoder2 Tensorflow

Model Card on HF 🤗: https://huggingface.co/RichardErkhov/HuggingFaceH4_-_starchat2-15b-v0.1-4bits

HuggingFaceH4 Starchat2 15B V0.1 4bits Parameters and Internals

Model Type

GPT-like

Use Cases

Areas:

chat, programming

Applications:

chat assistant, coding assistant

Supported Languages

primarily (English and 600+ programming languages)

Training Details

Data Sources:

HuggingFaceH4/ultrafeedback_binarized, HuggingFaceH4/orca_dpo_pairs

LLM Name	HuggingFaceH4 Starchat2 15B V0.1 4bits
Repository 🤗	https://huggingface.co/RichardErkhov/HuggingFaceH4_-_starchat2-15b-v0.1-4bits
Model Size	15b
Required VRAM	9.9 GB
Updated	2026-05-15
Maintainer	RichardErkhov
Model Type	starcoder2
Model Files	5.0 GB: 1-of-2 4.9 GB: 2-of-2
Model Architecture	Starcoder2ForCausalLM
Context Length	16384
Model Max Length	16384
Transformers Version	4.39.3
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	49154
Torch Data Type	float16

Rank the HuggingFaceH4 Starchat2 15B V0.1 4bits 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 HuggingFaceH4 Starchat2 15B V0.1 4bits

Best Alternatives	Context / RAM	Downloads	Likes
Starcoder2 15B	16K / 63.8 GB	8388	674
Starcoder2 15B Instruct V0.1	16K / 31.9 GB	597	105
Starcoder2 15B Finetuned Drake	16K / 63.8 GB	7	0
CodeFuse StarCoder2 15B	16K / 31.9 GB	18	1
Starchat2 15B V0.1	16K / 31.9 GB	352	112
Starcoder2 15B Instruct V0.1	16K / 53.4 GB	25	0
Dolphincoder Starcoder2 15B	16K / 31.9 GB	84	69
Dolphincoder Starcoder2 15B	16K / 31.9 GB	17	68
Starchat2 15B Sft V0.1	16K / 31.9 GB	12	5
Starcoder2 15B Instruct	16K / 31.9 GB	6	7

Note: green Score (e.g. "73.2") means that the model is better than RichardErkhov/HuggingFaceH4_-_starchat2-15b-v0.1-4bits.