What are the hardware requirements for Everyone Coder 4x7b Base?

Everyone Coder 4x7b Base requires approximately 48.3 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Everyone Coder 4x7b Base and how large is it?

Everyone Coder 4x7b Base is developed by rombodawg, a model with 24.2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Everyone Coder 4x7b Base perform on standard benchmarks?

Everyone Coder 4x7b Base has the following published scores: MMLU 64.27. Compare against reference models on this page or on the LLM Explorer leaderboards.

Everyone Coder 4x7b Base by rombodawg — VRAM 48.3GB, 32K context

Name: Everyone Coder 4x7b Base
Author: rombodawg

Everyone Coder 4x7b Base is an open-source language model by rombodawg. Features: 24.2b LLM, VRAM: 48.3GB, Context: 32K, License: cc-by-4.0, MoE, Code Generating, LLM Explorer Score: 0.16, Arc: 64.5, HellaSwag: 84.8, MMLU: 64.3, GSM8K: 63.5.

Codegen Endpoints compatible Merge Mixtral Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/rombodawg/Everyone-Coder-4x7b-Base

Everyone Coder 4x7b Base Benchmarks

ARC: 64.51 vs 96.7 (so35)^-33.3%

HellaSwag: 84.81 vs 95.3 (gpt4)^-11%

MMLU: 64.27 vs 88.3 (so35)^-27.2%

GSM8K: 63.46 vs 96.4 (so35)^-34.2%

LLME Score: 0.16038

^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)

Everyone Coder 4x7b Base (rombodawg/Everyone-Coder-4x7b-Base)

🌟 Advertise your project 🚀

Everyone Coder 4x7b Base Parameters and Internals

Model Type

coding specific

Additional Notes

This is the first model in the EveryoneLLM series, designed as a Mixtral-type model using community-finetuned experts.

Training Details

Data Sources:

fblgit/UNA-TheBeagle-7b-v1, LucciAI/openchat-3.5-0106-function-calling, WizardLM/WizardMath-7B-V1.1, cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser

LLM Name	Everyone Coder 4x7b Base
Repository 🤗	https://huggingface.co/rombodawg/Everyone-Coder-4x7b-Base
Model Size	24.2b
Required VRAM	48.3 GB
Updated	2026-05-23
Maintainer	rombodawg
Model Type	mixtral
Model Files	9.9 GB: 1-of-5 10.0 GB: 2-of-5 10.0 GB: 3-of-5 10.0 GB: 4-of-5 8.4 GB: 5-of-5
Generates Code	Yes
Model Architecture	MixtralForCausalLM
License	cc-by-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the Everyone Coder 4x7b Base

Model	Likes	Downloads	VRAM
Everyone Coder 4x7b Base GGUF	14	154	8 GB
Everyone Coder 4x7b Base GPTQ	4	2	12 GB
Everyone Coder 4x7b Base AWQ	2	10	13 GB

Best Alternatives to Everyone Coder 4x7b Base

Best Alternatives	Context / RAM	Downloads	Likes
Sixtyoneeighty 4x7B V1	32K / 48.3 GB	66	0
Sixtyoneeighty 4x7B V2	32K / 48.3 GB	0	0
Everyone Coder 4x7b Base GPTQ	32K / 12.5 GB	2	4
Everyone Coder 4x7b Base AWQ	32K / 13 GB	10	2

Rank the Everyone Coder 4x7b Base 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? 53972 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

Everyone Coder 4x7b Base by rombodawg