What are the hardware requirements for Speechless Codellama Orca 13B?

Speechless Codellama Orca 13B requires approximately 26 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 Codellama Orca 13B and how large is it?

Speechless Codellama Orca 13B is developed by uukuguy, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Speechless Codellama Orca 13B perform on standard benchmarks?

Speechless Codellama Orca 13B has the following published scores: MMLU 43.46. Compare against reference models on this page or on the LLM Explorer leaderboards.

Speechless Codellama Orca 13B by uukuguy — VRAM 26GB, 16K context

Name: Speechless Codellama Orca 13B
Author: uukuguy

Speechless Codellama Orca 13B is an open-source language model by uukuguy. Features: 13b LLM, VRAM: 26GB, Context: 16K, License: llama2, Code Generating, LLM Explorer Score: 0.12, Arc: 44.4, HellaSwag: 65.2, MMLU: 43.5, GSM8K: 6.

Arxiv:2308.12950 Codegen Dataset:garage-baind/open-plat... En Endpoints compatible Llama Llama2 Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/uukuguy/speechless-codellama-orca-13b

Speechless Codellama Orca 13B Parameters and Internals

Model Type

text generation, code synthesis

Use Cases

Areas:

Commercial applications, Research

Primary Use Cases:

Code synthesis, Code understanding tasks

Limitations:

Use in non-English languages, Legal and regulatory violations

Considerations:

Users must follow the Responsible Use Guide and perform safety testing.

Additional Notes

Carbon footprint for training was 65.3 tCO2eq, offset by Meta's sustainability program.

Supported Languages

en (fluent)

Training Details

Data Sources:

Llama 2 dataset

Methodology:

Fine-tuned with Orca dataset

Hardware Used:

A100-80GB GPUs

Model Architecture:

Auto-regressive language model with transformer architecture

Safety Evaluation

Methodologies:

English testing

Risk Categories:

Safety and ethical risks

Ethical Considerations:

Unpredictable outputs; must perform safety testing and tuning tailored to specific applications.

Input Output

Input Format:

Text input following Alpaca instruction format

Accepted Modalities:

text

Output Format:

Text output

LLM Name	Speechless Codellama Orca 13B
Repository 🤗	https://huggingface.co/uukuguy/speechless-codellama-orca-13b
Model Size	13b
Required VRAM	26 GB
Updated	2026-08-08
Maintainer	uukuguy
Model Type	llama
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3
Supported Languages	en
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.32.1
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32016
Torch Data Type	float16

Rank the Speechless Codellama Orca 13B 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 Codellama Orca 13B

Best Alternatives	Context / RAM	Downloads	Likes
NexusRaven V2 13B	16K / 26 GB	105	472
CodeLlama 13B Instruct Hf	16K / 26 GB	2469	160
CodeLlama 13B MORepair	16K / 26 GB	9	2
CodeLlama 13B Hf	16K / 26 GB	3466	117
Tora Code 13B V1.0	16K / 26 GB	878	15
CodeLlama 13B Python Hf	16K / 26 GB	558	51
...ma 13B Hf Truncated Embeddings	16K / 52.3 GB	5	0
...ma Airoboros Orca Platypus 13B	16K / 26 GB	117	0
Codellama 13B Oasst Sft V10	16K / 25.9 GB	184	70
CodeLlama 13B Hf	16K / 26 GB	224	0

Note: green Score (e.g. "73.2") means that the model is better than uukuguy/speechless-codellama-orca-13b.