What are the hardware requirements for Llama 2 Coder 7B?

Llama 2 Coder 7B requires approximately 13.5 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 2 Coder 7B and how large is it?

Llama 2 Coder 7B is developed by mrm8488, 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 Llama 2 Coder 7B perform on standard benchmarks?

Llama 2 Coder 7B has the following published scores: MMLU 46.25. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 2 Coder 7B by mrm8488 — VRAM 13.5GB, 4K context

Name: Llama 2 Coder 7B
Author: mrm8488

Llama 2 Coder 7B is an open-source language model by mrm8488. Features: 7b LLM, VRAM: 13.5GB, Context: 4K, License: apache-2.0, Code Generating, HF Score: 50, LLM Explorer Score: 0.13, Arc: 54, HellaSwag: 78.4, MMLU: 46.3, TruthfulQA: 38.5, WinoGrande: 75.5, GSM8K: 7.1.

Code Codegen Coding Dataset:huggingfaceh4/codealpa... Deploy:azure Doi:10.57967/hf/0931 Endpoints compatible Generated from trainer Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/mrm8488/llama-2-coder-7b

Llama 2 Coder 7B Benchmarks

ARC: 54.01 vs 96.7 (so35)^-44.1%

HellaSwag: 78.35 vs 95.3 (gpt4)^-17.8%

MMLU: 46.25 vs 88.3 (so35)^-47.6%

TruthfulQA: 38.49 vs 59 (gpt4)^-34.8%

WinoGrande: 75.45 vs 87.5 (gpt4)^-13.8%

GSM8K: 7.13 vs 96.4 (so35)^-92.6%

LLME Score: 0.12517

^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)

Llama 2 Coder 7B (mrm8488/llama-2-coder-7b)

🌟 Advertise your project 🚀

Llama 2 Coder 7B Parameters and Internals

Model Type

text generation, code generation

Use Cases

Areas:

code assistance, instruction-driven code tasks, commercial

Applications:

software development, code refactoring, coding education

Primary Use Cases:

Coding assistant, Instruction-driven code assistance

Supported Languages

programming_languages (.all programming languages, focusing on instruction-driven tasks.)

Training Details

Data Sources:

HuggingFaceH4/CodeAlpaca_20K

Data Volume:

20K instruction-following data

Methodology:

QLoRA fine-tuning with PEFT library

Model Architecture:

Llama-2-Chat fine-tuned with QLoRA

Safety Evaluation

Methodologies:

Human evaluations for helpfulness and safety

Findings:

On par with ChatGPT and PaLM for dialogue use cases

Input Output

Input Format:

Instruction as a prompt

Accepted Modalities:

text

Output Format:

Generated text solution

LLM Name	Llama 2 Coder 7B
Repository 🤗	https://huggingface.co/mrm8488/llama-2-coder-7b
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-04-30
Maintainer	mrm8488
Model Type	llama
Model Files	10.0 GB: 1-of-2 3.5 GB: 2-of-2
Supported Languages	code
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.31.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the Llama 2 Coder 7B

Model	Likes	Downloads	VRAM
Llama 2 Coder 7B GGUF	15	928	2 GB
Llama 2 Coder 7B AWQ	3	79	3 GB
Llama 2 Coder 7B GPTQ	10	10	3 GB

Best Alternatives to Llama 2 Coder 7B

Best Alternatives	Context / RAM	Downloads	Likes
Deepseek Coder 6.7B Instruct	16K / 13.5 GB	215811	491
CodeLlama 7B Instruct Hf	16K / 13.5 GB	224984	255
CodeLlama 7B Hf	16K / 13.5 GB	63145	375
GetCode Slerp	16K / 13.6 GB	139	1
Wizardllama 7B	16K / 13.5 GB	111	0
Codellama 7B Hf ReFT GSM8k	16K / 13.5 GB	864	1
MathCoder2 CodeLlama 7B	16K / 13.5 GB	12	5
CodeLlama 7B Python Hf	16K / 13.5 GB	2488	144
GoLLIE 7B	16K / 40.5 GB	2070	30
Stack Codellama 7B Inst	16K / 13.5 GB	92	0

Note: green Score (e.g. "73.2") means that the model is better than mrm8488/llama-2-coder-7b.

Rank the Llama 2 Coder 7B 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

Llama 2 Coder 7B by mrm8488