SAVRN
Search Contact SAVRN

Open-weight model

lexi-coder-v4.4

by Reallexi LLC reallexi/lexi-coder-v4.4

lexi-coder-v4.4 is an open-weight model from Reallexi LLC. It has 3.8B parameters and a 131,072-token context. At 16-bit it needs about 9.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 1.2k downloads a month.

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.

Parameters3.8B
Context131,072
Weights10.2 GB
License
AccessOpen weights
Monthly Downloads1.2k

Runs On

What it takes to serve lexi-coder-v4.4 (3.8B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 7.7 GB 9.2 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 3.8 GB 4.6 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 1.9 GB 2.3 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

lexi-coder-v4.4 on every accelerator the SAVRN Index prices, at every precision

Model Card

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.

Excerpt from the card by Reallexi LLC.

Configuration

Architecture
Phi3ForCausalLM
Context length (tokens)
131,072
Layers
32
Hidden size
3,072
Feed-forward size
8,192
Attention heads
24
Key/value heads
8
Vocabulary size
200,064
Sliding window (tokens)
262,144
Model type
phi3

Identity and Version

Repository
reallexi/lexi-coder-v4.4
Publisher
Reallexi LLC
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
3.8B parameters
Languages
Not stated by the source
Revision
5ef5f75129bc9dec99728d54f8b7172cba6843fd
First published
2026-09-06
Last updated
2026-09-18

Files and Weights

22 files, 10.2 GB in total. The weights are 5 files totalling 10.2 GB in gguf, safetensors.

Weights5 files · 10.2 GB
Configuration7 files · 23.2 KB
Tokenizer4 files · 21.9 MB
Documentation3 files · 2.6 KB
Other2 files · 72.5 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
lexi-coder-v4-4-q4_k_m.ggufWeights2.5 GB 56086ac86af3
model-00001-of-00004.safetensorsWeights2.0 GB be21677d3027
model-00002-of-00004.safetensorsWeights1.9 GB fd73c1dd4e89
model-00003-of-00004.safetensorsWeights2.0 GB 5919bf46fe4a
model-00004-of-00004.safetensorsWeights1.8 GB 491cb7d2321e
added_tokens.jsonConfiguration249 B
config.jsonConfiguration2.6 KB
generation_config.jsonConfiguration168 B
model.safetensors.index.jsonConfiguration16.3 KB
reallexi-model.jsonConfiguration626 B
samples.jsonConfiguration2.6 KB
special_tokens_map.jsonConfiguration587 B
NOTICEDocumentation247 B
README.mdDocumentation364 B
SAMPLES.mdDocumentation2.0 KB
chat_template.jinjaOther423 B
training_curve.pngOther72.0 KB
.gitattributesRepository1.6 KB
merges.txtTokenizer2.4 MB
tokenizer.jsonTokenizer15.5 MB 5ae4719cd8d4
tokenizer_config.jsonTokenizer508 B
vocab.jsonTokenizer3.9 MB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
10.2 GB
Download from Reallexi LLC

Released by Reallexi LLC through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published10.2 GB
16-bit7.7 GB
8-bit3.8 GB
4-bit1.9 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About lexi-coder-v4.4

How much GPU memory does lexi-coder-v4.4 need?

About 9.2 GB at 16-bit and 2.3 GB at 4-bit: the weights (3.8B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run lexi-coder-v4.4 on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

What is lexi-coder-v4.4's context length?

131,072 tokens, from the maximum position embeddings in its published configuration.