GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
nbeerbower
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
nbeerbower
Model Tree
Base
google/gemma-4-31B-it
Adapter
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
python
import torchfrom transformers import AutoModelForCausalLMfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("google/gemma-4-31B-it", dtype=torch.bfloat16)model = PeftModel.from_pretrained(base, "nbeerbower/Gemma4-Gutenberg-31B-LoRA")# or .merge_and_unload() for a standalone full model
ORPO (β=0.1) on schneewolflabs/Athanorlite-DPO
(14,816 pairs; the Gutenberg "Encore" mix + more). LR 5e-5 cosine, eff batch 32,
max_len 2048, 1 epoch on 1× NVIDIA GB10, via
Merlina. reward_accuracy 0.18 → 0.91.
Full details on the merged model card.
Apache-2.0 (matching the Gemma 4 base).