positron-ai

google_gemma-4-E4B-it-ingest-best-gptq-permuted

README

License: apache-2.0

Quantized checkpoint for CI ingestion and regression tests.

GPTQ: 4-bit, group size 64, symmetric, activation order enabled.

Published as a test fixture; no serving-qualification or accuracy claim.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Model Details

Model Provider

positron-ai

Model Tree

Base

google/gemma-4-E4B-it

Quantized

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated Endpoints