GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
keithtyser
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
keithtyser
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3.5-9Bmodel-forge/qwen35-9b-base-nvfp4-modeloptbasepublic_quantized_modelFalsenvfp4spark_single_node_validatedThis card documents the published Hub artifact. The Model Forge release gates passed before upload, and the artifact was published on 2026-06-07.
Repository evidence:
model-forge-evidence/eval_results/scores.csvmodel-forge-evidence/full_eval_results/scores.csvmodel-forge-evidence/full_eval_manifest/full_eval_manifest_manifest.jsonmodel-forge-evidence/serving_card/quantization_card.jsonmodel-forge-evidence/quantization_card/quantization_card.jsonmodel-forge-evidence/promotion_report/promotion_report_nvfp4_evidence_gate.jsonmodel-forge-evidence/hub_publish.jsonQuantization summary:
configs/model_families/qwen35_9b.yaml./forge hf plan-model qwen35_9b base_nvfp4_modelopt --release-class public_quantized_modelThis is a released NVIDIA ModelOpt NVFP4 artifact, not a placeholder or planned release. The model-forge-evidence/ directory is the release record.
The artifact requires an NVIDIA/CUDA, Transformers, and ModelOpt stack that supports its exported NVFP4 format. Pin compatible versions before deployment and validate loading in the target serving environment. A portable first step is:
bash
hf download keithtyser/model-forge-qwen35-9b-base-nvfp4-modelopt --local-dir ./model
The published evaluation evidence covers text-generation serving. Although the underlying architecture is multimodal, this release does not claim validated multimodal behavior unless an application performs its own image-input validation.
Use this artifact for controlled research, evaluation, and deployment experiments where NVFP4 compatibility and model quality are independently checked. Quantization can change accuracy, calibration, and safety behavior. Review the repository evidence and run task-specific and safety evaluations before production use. Throughput measurements are specific to the published DGX Spark evaluation setup and are not a universal speed guarantee.