GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
ucsbcit
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ucsbcit
Model Tree
OpenGVLab/InternVL3_5-38B-Flash
Input Modalities
Output Modalities
Supported Functionality
OpenGVLab/InternVL3_5-38B-FlashLinear layersllmcompressor (Post-Training Quantization / PTQ)ultrachat-200k (train_sft)The model was quantized using Neural Magic's llm-compressor framework.
Post-training quantization (PTQ) was applied directly to the language backbone (model.language_model). This strategy ensures that all heavy Linear projections in the main LLM layers are converted to FP8 for maximum speedup and reduced VRAM footprint, while preserving the vision architecture intact.
python
from llmcompressor import oneshotfrom llmcompressor.modifiers.quantization import QuantizationModifierrecipe = QuantizationModifier(targets="Linear",scheme="FP8",ignore=["lm_head"])oneshot(model=model.language_model,tokenizer=tokenizer,dataset="ultrachat-200k",splits="train_sft[:512]",recipe=recipe,max_seq_length=2048,num_calibration_samples=512,)