What are the hardware requirements for Glaive Coder 7B?

Glaive Coder 7B requires approximately 27 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 Glaive Coder 7B and how large is it?

Glaive Coder 7B is developed by glaiveai, 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 Glaive Coder 7B perform on standard benchmarks?

Glaive Coder 7B has the following published scores: MMLU 37.15. Compare against reference models on this page or on the LLM Explorer leaderboards.

Glaive Coder 7B by glaiveai — VRAM 27GB, 16K context

Name: Glaive Coder 7B
Author: glaiveai

Glaive Coder 7B is an open-source language model by glaiveai. Features: 7b LLM, VRAM: 27GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.13, Arc: 42.7, HellaSwag: 64.7, MMLU: 37.2, GSM8K: 5.2.

Code Codegen Dataset:glaiveai/glaive-code-a... En Endpoints compatible Instruct Llama Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/glaiveai/glaive-coder-7b

Glaive Coder 7B Parameters and Internals

Model Type

code generation

Use Cases

Areas:

code assistance

Applications:

single instruction following, multi-turn conversations

Primary Use Cases:

As a code assistant

Additional Notes

Join the Code Models Arena for better understanding of user preference and suggest improvements via Discord.

Supported Languages

en (Subtype: Engilsh)

Training Details

Data Sources:

glaiveai/glaive-code-assistant

Data Volume:

~140k programming related problems and solutions

Methodology:

Fine-tuned on the CodeLlama-7b model. Uses a specific prompt format similar to CodeLlama-7b-Instruct.

Input Output

Input Format:

~~[INST] <> {{ system_prompt }} <> {{ user_msg }} [/INST] {{ model_answer }}

Output Format:

Generates code outputs based on the provided instruction.

LLM Name	Glaive Coder 7B
Repository 🤗	https://huggingface.co/glaiveai/glaive-coder-7b
Model Size	7b
Required VRAM	27 GB
Updated	2026-07-30
Maintainer	glaiveai
Model Type	llama
Instruction-Based	Yes
Model Files	27.0 GB
Supported Languages	en
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.32.0
Tokenizer Class	CodeLlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32017
Torch Data Type	float32

Rank the Glaive Coder 7B 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 Glaive Coder 7B

Best Alternatives	Context / RAM	Downloads	Likes
Deepseek Coder 6.7B Instruct	16K / 13.5 GB	535311	507
CodeLlama 7B Instruct Hf	16K / 13.5 GB	58587	258
GetCode Slerp	16K / 13.6 GB	87	1
Stack Codellama 7B Inst	16K / 13.5 GB	66	0
CodeV CL 7B	16K / 13.5 GB	430	1
CodeLlama 7B Instruct Hf	16K / 13.5 GB	2313	63
...deLlama 7B Instruct Hf 8bits Q	16K / 4.2 GB	17	1
Llama 2 7B Chat Finetune5	16K / 13.8 GB	3	1
...ama 7B Instruct Hf Dequantized	16K / 13.5 GB	197	0
CodeLLama SFT FILTERED	16K / 13.5 GB	9	0

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