What are the hardware requirements for Lexi Coder V4.3?

Lexi Coder V4.3 requires approximately 7.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Lexi Coder V4.3 and how large is it?

Lexi Coder V4.3 is developed by reallexi, a model with 3.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Lexi Coder V4.3?

Lexi Coder V4.3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Lexi Coder V4.3 by reallexi — VRAM 7.7GB, 128K context

Name: Lexi Coder V4.3
Author: reallexi

Lexi Coder V4.3 is an open-source language model by reallexi. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: other, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.31.

Ai-model-builder Base model:adapter:microsoft/p... Base model:microsoft/phi-4-min... Codegen Conversational Custom code Endpoints compatible Finetuned Gguf Instruct Lora Phi3 Q4 Quantized Reallexi Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/reallexi/lexi-coder-v4.3

Lexi Coder V4.3 Parameters and Internals

LLM Name	Lexi Coder V4.3
Repository 🤗	https://huggingface.co/reallexi/lexi-coder-v4.3
Base Model(s)	Phi 4 Mini Instruct microsoft/Phi-4-mini-instruct
Model Size	3.8b
Required VRAM	7.7 GB
Updated	2026-08-11
Maintainer	reallexi
Model Type	phi3
Instruction-Based	Yes
Model Files	7.7 GB 2.5 GB 2.0 GB: 1-of-4 1.9 GB: 2-of-4 2.0 GB: 3-of-4 1.8 GB: 4-of-4
GGUF Quantization	Yes
Quantization Type	q4\|gguf\|q4_k
Generates Code	Yes
Model Architecture	Phi3ForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	5.3.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	200064

Rank the Lexi Coder V4.3 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 Lexi Coder V4.3

Best Alternatives	Context / RAM	Downloads	Likes
Omega Coder Phi 3 Mini 1K	4K / 15.4 GB	5	0
Coder Phi 3 Mini 4K Instruct	4K / 7.7 GB	13	0