What are the hardware requirements for Speechless Starcoder2 15B?

Speechless Starcoder2 15B requires approximately 31.9 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 Speechless Starcoder2 15B and how large is it?

Speechless Starcoder2 15B is developed by uukuguy, 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 Speechless Starcoder2 15B?

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

Speechless Starcoder2 15B by uukuguy — VRAM 31.9GB, 16K context

Name: Speechless Starcoder2 15B
Author: uukuguy

Speechless Starcoder2 15B is an open-source language model by uukuguy. Features: 15b LLM, VRAM: 31.9GB, Context: 16K, License: bigcode-openrail-m, Quantized, LLM Explorer Score: 0.11.

Arxiv:2004.05150 Arxiv:2205.14135 Arxiv:2207.14255 Arxiv:2305.13245 Arxiv:2402.19173 Code Dataset:bigcode/the-stack-v2-t... Endpoints compatible Fp16 Model-index Quantized Region:us Safetensors Sharded Starcoder2 Tensorflow

Model Card on HF 🤗: https://huggingface.co/uukuguy/speechless-starcoder2-15b

Speechless Starcoder2 15B Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

research, programming assistance

Applications:

code generation, programming help

Limitations:

may generate inefficient, buggy, or exploitable code

Additional Notes

Not an instruction model; Contains code from permissive license only.

Training Details

Data Sources:

The Stack v2, GitHub, Arxiv, Wikipedia

Data Volume:

4+ trillion tokens

Methodology:

Fill-in-the-Middle objective

Context Length:

16384

Hardware Used:

NVIDIA Eos Supercomputer, 1024 x H100 GPUs

Model Architecture:

Transformer decoder with grouped-query and sliding window attention

Input Output

Input Format:

Alpaca instruction format

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Ensure proper context is provided; model not suited for instruction following

LLM Name	Speechless Starcoder2 15B
Repository 🤗	https://huggingface.co/uukuguy/speechless-starcoder2-15b
Model Size	15b
Required VRAM	31.9 GB
Updated	2026-07-22
Maintainer	uukuguy
Model Type	starcoder2
Model Files	4.9 GB: 1-of-7 5.0 GB: 2-of-7 5.0 GB: 3-of-7 5.0 GB: 4-of-7 5.0 GB: 5-of-7 5.0 GB: 6-of-7 2.0 GB: 7-of-7
Quantization Type	fp16
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	float16

Rank the Speechless Starcoder2 15B 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 Speechless Starcoder2 15B

Best Alternatives	Context / RAM	Downloads	Likes
Starcoder2 15B	16K / 63.8 GB	8388	674
Starcoder2 15B AWQ	16K / 9.2 GB	8	1
Starcoder2 15B Instruct V0.1	16K / 31.9 GB	597	105
...rCoder2 15B Instruct V0.1 GGUF	16K / 6.2 GB	412	0
StarCoder2 15B GGUF	16K / 6.2 GB	1731	31
...rCoder2 15B Instruct V0.1 GGUF	16K / 6.2 GB	261	0
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

Note: green Score (e.g. "73.2") means that the model is better than uukuguy/speechless-starcoder2-15b.