What are the hardware requirements for CodeLlama 13B Instruct Fp16?

CodeLlama 13B Instruct Fp16 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 CodeLlama 13B Instruct Fp16 and how large is it?

CodeLlama 13B Instruct Fp16 is developed by TheBloke, 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 CodeLlama 13B Instruct Fp16 perform on standard benchmarks?

CodeLlama 13B Instruct Fp16 has the following published scores: MMLU 38.77. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeLlama 13B Instruct Fp16 by TheBloke — VRAM 26GB, 16K context

Name: CodeLlama 13B Instruct Fp16
Author: TheBloke

CodeLlama 13B Instruct Fp16 is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 26GB, Context: 16K, License: llama2, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.12, Arc: 44.6, HellaSwag: 64.9, MMLU: 38.8, GSM8K: 12.7.

Codegen Codellama Custom code Endpoints compatible Fp16 Instruct Llama Llama2 Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-fp16

CodeLlama 13B Instruct Fp16 Parameters and Internals

Model Type

instruction following, code synthesis, text generation

Use Cases

Areas:

Commercial, Research

Applications:

Code synthesis, Code understanding, Code assistive applications

Primary Use Cases:

Code assistant, Code generation

Limitations:

Use in languages other than English, Code use not covered by safety evaluations

Considerations:

Perform safety testing tailored to specific applications.

Additional Notes

Model variants are designed for Python and safer deployment applications.

Supported Languages

English (Full support), Python (Highly specialized support), Other programming languages (Partial support)

Training Details

Methodology:

Fine-tuned with instruction data

Context Length:

100000

Hardware Used:

A100-80GB

Model Architecture:

Autoregressive, transformer architecture

LLM Name	CodeLlama 13B Instruct Fp16
Repository 🤗	https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-fp16
Base Model(s)	...lama 13B Instruction Finetune2 ashwincv0112/code-llama-13b-instruction-finetune2
Model Size	13b
Required VRAM	26 GB
Updated	2026-07-22
Maintainer	TheBloke
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3
Quantization Type	fp16
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.32.0
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 CodeLlama 13B Instruct Fp16 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 CodeLlama 13B Instruct Fp16

Best Alternatives	Context / RAM	Downloads	Likes
...Llama 13B Instruct Hf 4bit MLX	16K / 7.8 GB	113	3
...13B Instruct Nf4 Fp16 Upscaled	16K / 26 GB	6	0
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 Instruct Hf	16K / 26 GB	369	29
TableLLM 13B	16K / 26 GB	98	34
CodeLlama 13B Instruct GGUF	16K / 5.4 GB	611	2
NexusRaven 13B	16K / 26 GB	37	106
CodeLlama 13B Instruct AWQ	16K / 7.2 GB	261	9

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-13B-Instruct-fp16.