GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
GammaAGI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
GammaAGI
Model Tree
Base
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Adapter
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Train a bounded, traceable EvoStream adapter on top of the accepted Nano scaffold using verified donor, code, reasoning, safety, and Omni contracts.
OK2.0759041.511613[0.540352, 0.528112, 0.475032, 0.54333, 2.226267, 2.219524, 2.185869, 2.20969, 2.226476, 2.219999, 2.267029, 2.153279, 3.287959, 3.343807, 3.332414, 3.360451, 0.494826, 0.491685, 0.440102, 0.501152, 2.135163, 2.165602, 2.127513, 2.1284, 2.192846, 2.142152, 2.218314, 2.099888, 3.232536, 3.278952, 3.264213, 3.277984, 0.425896, 0.429326, 0.371165, 0.428833, 2.009046, 1.967234, 1.954897, 1.955407, 2.048863, 2.015757, 2.060079, 1.891168, 3.07378, 3.119954, 3.089393, 3.075348, 0.325838, 0.332749, 0.281433, 0.329397, 1.732414, 1.708836, 1.714866, 1.648485, 1.829787, 1.758606, 1.770442, 1.653636, 2.797887, 2.816635, 2.785876, 2.795174]1104842240.00348658/workspace/gamma_30b_alpha_lora/input/gamma30_v2_4_2_qwen36_ultracompact_ladder_pack_20260615.jsonl16Run strict v2.1 evaluation, then merge/unload or consolidate only if accepted.