G

Gemma-4-31B-Lexide

Lexide Programming

No ratings yet(0)
Prose
—(0)
Intelligence
—(0)
Knowledge
—(0)
Instruction Following
—(0)
Coding
—(0)
Steerability
—(0)
Sign in to vote

Ratings reflect this model as run on Arli AI.

Gemma-4-31B-Lexide is a text generation model available on Arli AI. It offers 31B parameters, 262K token context, reasoning support, vision input. Recommended use: Lexide Programming. Run it through the OpenAI-compatible chat completions API with unlimited requests and zero-log privacy.

View on Hugging FaceBack to Models

Hourly Usage

No hourly usage data available

Token Usage

Input (24H)

0

Output (24H)

0

Input (7D)

0

Output (7D)

0

Performance Metrics

Typical Total Time

N/A

Typical TTFT

N/A

Typical Input TPS

N/A

Typical Output TPS

N/A

Model Information

Context Size

262144

Quantization

r128 on FP8

Engine

vllm

Creation Method

Finetune

Model Class

Gemma-4-31B - LoRA

Chat Template

Gemma4

Reasoning

Yes

Vision

Yes

Parameters

31B

Added At

10/31/2026

Use Gemma-4-31B-Lexide with the Arli AI API

Gemma-4-31B-Lexide is available through an OpenAI-compatible chat completions endpoint. Point any OpenAI SDK at https://api.arliai.com/v1, pass Gemma-4-31B-Lexide as the model, and requests are served without logging.

cURL

curl https://api.arliai.com/v1/chat/completions \
  -H "Authorization: Bearer $ARLIAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Gemma-4-31B-Lexide",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.arliai.com/v1",
    api_key="YOUR_ARLIAI_API_KEY",
)

response = client.chat.completions.create(
    model="Gemma-4-31B-Lexide",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

See the text generation docs for every parameter, or read the quick start guide to make your first request.

Similar models

license: gemma base_model: google/gemma-4-31B-it library_name: peft pipeline_tag: text-generation language:

  • multilingual tags:
  • lora
  • gemma
  • morphology
  • part-of-speech
  • lemmatization
  • dependency-parsing
  • language-learning

lexide-gemma-4-31B-it

A LoRA fine-tune of google/gemma-4-31B-it that performs multilingual grammatical analysis for the lexide language-learning project: given a sentence, it emits a structured analysis (part of speech, lemma, and dependency information) token by token.

Role

This is the original "Gemma tagger." It has since been superseded online by anchpop/lexide-parsley — a small XLM-RoBERTa encoder tagger that runs on CPU — but this model is retained as the teacher behind it:

  • Silver-label teacher — generates the large-scale training data parsley distills from.
  • Gold reference — used to produce the curated cleaned_*.jsonl evaluation labels.
  • Fallback — still serves languages (e.g. Japanese) where the encoder tagger is weaker.

It is served with vLLM (scale-to-zero) as a LoRA adapter merged onto the base model.

Training

Base modelgoogle/gemma-4-31B-it
MethodLoRA (PEFT), task_type=CAUSAL_LM
Rank / alphar = 64, α = 128
Target modulesq_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Usage

Load the adapter on top of the base model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "google/gemma-4-31B-it"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, "anchpop/lexide-gemma-4-31B-it")

License

This is a derivative of Google's Gemma and is distributed under the Gemma Terms of Use. Use is subject to those terms and the Gemma Prohibited Use Policy.