lexi-coder-v4.4

lexi-coder-v4.4 by Reallexi LLC AI Model Builder — llm.reallexi.io

Copyright (c) 2026 Reallexi LLC. All rights reserved.

A standalone model of 3.85B parameters, derived from reallexi/lexi-coder-v4.3.

The adapter has been merged into the base weights, so no PEFT adapter is needed at runtime.

Size and requirements

Parameters	3,847,556,096 (3.85B)
Weights on disk	7.15 GB
Trained context length	2,048 tokens
Base model	reallexi/lexi-coder-v4.3

Approximate memory to hold the weights. Add context and runtime overhead on top.

Precision	Weights
FP16 / BF16	7.17 GB
8-bit (Q8_0)	3.58 GB
4-bit (Q4_K_M)	1.97 GB

Training

Strategy	lora
Adapter	Auto LoRA
LoRA rank / alpha	8 / 16
Dataset	reallexi/lexi-coder-v3-datasest
Samples learned	315,000 (through phase 37 of 174)
Training steps	15,000
Epochs	3

Before / after samples

The same prompts, drawn from the training data, run through the base model before training and the finished model after. This shows what the run changed on representative prompts -- it is not a benchmark. Full outputs are in SAMPLES.md and samples.json alongside this file.

Prompt: ksTogMofwfdLnSKugOkBwsvfAd9O+p9Lig6XFO0hK0HZCFv9gpNP94iDN4bCPgA5WiBoAwzOxoOPsFCxKXxc0m6Pr6ULGX32oX3almYiL6e2JLE99kwhe+wbDVbLnOvp/Hs9omU9yu44AaTAebGhxAjvRSDnfulq…

• Before: 8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+
• After: 8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+8+

Prompt: +n%DjHoNAlzRkGHx9IJz$4Q@=f*gsS{%Zk_blReDzmal^2PJ+uG<dg%7$_LN2w=iSx&dhGNtZoe)JMb;8kg^P_vhAv+Iw|VD&;M=m5FKx|yQ!<OVtjm>sEljIHA7rd=&A_0ntD;E?|rdV|Mserx*=SDT+58+…

• Before: &%#-1!%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&
• After: &%#x^%&`&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%&%

Prompt: def solve(string): n, x, t = map(int, string.split()) return str((n + x - 1) // x * t) if name

• Before: == "main": print(solve()) exit()

  main = file

  import os, sys

  file = open(os.path.join(main, "input"), "r")

  H, W = map(int, file.readline().rstrip().split())

  a = []

  for i in range(H):

  a.append(list(map(int,

• After: == "main": print(solve()) exit()

  for i in range(1, 1000):

  if n % i == 0:

  print(i)

  exit()

  print(n) # 1000

  print(n//i) # 200

  print(200 * 5) # 100

Training curve

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("lexi-coder-v4.4")
tokenizer = AutoTokenizer.from_pretrained("lexi-coder-v4.4")

License and attribution

The effective terms are inherited from the base model and the training data, which are not necessarily the same as this project's own license. Review both before redistributing.

• Base model: reallexi/lexi-coder-v4.3

• Training data: reallexi/lexi-coder-v3-datasest

Copyright (c) 2026 Reallexi LLC. All rights reserved.

Produced by Reallexi LLC AI Model Builder from training job #1971. Core: https://llm.reallexi.io

Who, where, and what platform trained this?

Produced by Reallexi LLC on Reallexi AI Model Builder, a local-first training platform (https://llm.reallexi.io). Hugging Face repository: reallexi/lexi-coder-v4.4. Copyright (c) 2026 Reallexi LLC. All rights reserved.