What are the hardware requirements for CodeLlama 7B Fp16?

CodeLlama 7B Fp16 requires approximately 13.5 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 7B Fp16 and how large is it?

CodeLlama 7B Fp16 is developed by TheBloke, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CodeLlama 7B Fp16 perform on standard benchmarks?

CodeLlama 7B Fp16 has the following published scores: MMLU 59.37. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeLlama 7B Fp16 by TheBloke — VRAM 13.5GB, 16K context

Name: CodeLlama 7B Fp16
Author: TheBloke

CodeLlama 7B Fp16 is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 13.5GB, Context: 16K, License: llama2, Quantized, Code Generating, HF Score: 57.2, LLM Explorer Score: 0.11, Arc: 60.8, HellaSwag: 81.2, MMLU: 59.4, TruthfulQA: 44.7, WinoGrande: 73.2, GSM8K: 23.9.

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

Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-7B-fp16

CodeLlama 7B Fp16 Benchmarks

ARC: 60.75 vs 96.7 (so35)^-37.2%

HellaSwag: 81.15 vs 95.3 (gpt4)^-14.8%

MMLU: 59.37 vs 88.3 (so35)^-32.8%

TruthfulQA: 44.65 vs 59 (gpt4)^-24.3%

WinoGrande: 73.24 vs 87.5 (gpt4)^-16.3%

GSM8K: 23.88 vs 96.4 (so35)^-75.2%

LLME Score: 0.11145

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

CodeLlama 7B Fp16 (TheBloke/CodeLlama-7B-fp16)

🌟 Advertise your project 🚀

CodeLlama 7B Fp16 Parameters and Internals

Model Type

text generation

Use Cases

Areas:

commercial, research

Applications:

code synthesis, understanding tasks, Python programming, code assistant

Primary Use Cases:

code synthesis and understanding tasks, handle the Python programming language

Limitations:

Use in any manner that violates applicable laws or regulations, Use in languages other than English

Considerations:

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

Supported Languages

English (proficient)

Training Details

Data Sources:

same data as Llama 2 with different weights

Context Length:

100000

Hardware Used:

A100-80GB (TDP of 350-400W)

Model Architecture:

autoregressive language models using optimized transformer architectures

Safety Evaluation

Ethical Considerations:

Testing conducted to date has been in English and has not covered all scenarios. Outputs cannot be predicted in advance and may be inaccurate or objectionable.

Input Output

Input Format:

text only

Accepted Modalities:

text

Output Format:

text only

Performance Tips:

Load the FP16 models with `trust_remote_code=True` for correct results.

LLM Name	CodeLlama 7B Fp16
Repository 🤗	https://huggingface.co/TheBloke/CodeLlama-7B-fp16
Base Model(s)	Code Llama 7B Text To Sql philschmid/code-llama-7b-text-to-sql
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-04-10
Maintainer	TheBloke
Model Type	llama
Model Files	10.0 GB: 1-of-2 3.5 GB: 2-of-2
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

Best Alternatives to CodeLlama 7B Fp16

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 7B Java 16bit	16K / 13.5 GB	7	0
Codellama 7B Bnb 4bit	16K / 3.9 GB	3214	9
...ruct Solidity Bnb 4bit Smashed	16K / 4.2 GB	6	0
...lama 7B Tofuagent Contpretrain	16K / 13.5 GB	5	0
...B Instruct Hf Bnb 4bit Smashed	16K / 4.2 GB	6	0
CodeLlama 7B Python Onnx Fp16	16K / GB	5	1
CodeLlama 7B Python 4bit MLX	16K / 4 GB	392	14
...eLlama 7B Instruct Hf 4bit MLX	16K / 4.2 GB	94	2
...pMagic Coder 7B 8.0bpw H8 EXL2	16K / 6.9 GB	2	1
CodelLama7B Inst DPO 7K Mlx	16K / 4.2 GB	33	3

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-7B-fp16.

Rank the CodeLlama 7B Fp16 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53472 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

CodeLlama 7B Fp16 by TheBloke

» All LLMs » TheBloke » CodeLlama 7B Fp16 URL Share it on

CodeLlama 7B Fp16 Benchmarks

CodeLlama 7B Fp16 Parameters and Internals

Best Alternatives to CodeLlama 7B Fp16

Rank the CodeLlama 7B Fp16 Capabilities

What open-source LLMs or SLMs are you in search of? 53472 in total.