What are the hardware requirements for Ct2fast Codellama 13B Instruct Hf?

Ct2fast Codellama 13B Instruct Hf requires approximately 13 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ct2fast Codellama 13B Instruct Hf and how large is it?

Ct2fast Codellama 13B Instruct Hf is developed by piratos, a model with 13b 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 Ct2fast Codellama 13B Instruct Hf?

Ct2fast Codellama 13B Instruct Hf is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ct2fast Codellama 13B Instruct Hf by piratos — VRAM 13GB

Name: Ct2fast Codellama 13B Instruct Hf
Author: piratos

Ct2fast Codellama 13B Instruct Hf is an open-source language model by piratos. Features: 13b LLM, VRAM: 13GB, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.08.

Code Codegen Endpoints compatible Instruct Llama2 Region:us

Model Card on HF 🤗: https://huggingface.co/piratos/ct2fast-codellama-13b-instruct-hf

Ct2fast Codellama 13B Instruct Hf Parameters and Internals

Model Type

Text Generation, Code Synthesis, Understanding

Use Cases

Areas:

Commercial, Research

Applications:

Code synthesis, Understanding tasks, Code assistant

Primary Use Cases:

General code synthesis and understanding, Python handling, Safer deployment for code assistant

Limitations:

Not designed for use in languages other than English, Potential for generating inaccurate or objectionable responses

Considerations:

Developers should perform safety testing and tuning tailored to their specific applications.

Supported Languages

English (High proficiency), Programming Languages (Relevant programming languages)

Training Details

Data Sources:

Same data as Llama 2 with different weights

Training Time:

From January 2023 to July 2023

Hardware Used:

Meta’s Research Super Cluster, A100-80GB GPUs (350-400W)

Model Architecture:

Optimized transformer architecture

Input Output

Input Format:

Text input only

Output Format:

Text output only

LLM Name	Ct2fast Codellama 13B Instruct Hf
Repository 🤗	https://huggingface.co/piratos/ct2fast-codellama-13b-instruct-hf
Model Size	13b
Required VRAM	13 GB
Updated	2026-06-27
Maintainer	piratos
Instruction-Based	Yes
Model Files	13.0 GB
Supported Languages	code
Generates Code	Yes
Model Architecture	AutoModel
License	llama2
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>

Rank the Ct2fast Codellama 13B Instruct Hf 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 Ct2fast Codellama 13B Instruct Hf

Best Alternatives	Context / RAM	Downloads	Likes
Codellama 7B Instruct GGUF	0K / 2.8 GB	166	1
Codellama 13B Instruct GGUF	0K / 13.8 GB	28	0
CodeLlama 13B Instruct GGUF	0K / 5.4 GB	3987	132
CodeLlama 13B Instruct GGML	0K / 5.7 GB	11	19

Note: green Score (e.g. "73.2") means that the model is better than piratos/ct2fast-codellama-13b-instruct-hf.