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/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3.6-27Bmodel-forge/qwen36-27b-local-ft-v4-nvfp4-attn-output-bf16-modeloptlocal_ft_v4public_quantized_modelFalsenvfp4_attention_output_bf16spark_cluster_validatedmodel.safetensors.index.jsonThis card was generated from a Model Forge Hub plan that passed the configured public quantized-model release gates. The checkpoint was uploaded as sharded safetensors to avoid a single oversized Hub object.
Provided evidence:
reports/generated/serving_evals/qwen36_27b_local_ft_v4_nvfp4_attention_output_bf16_modelopt_tp2_serving_eval_20260606/scores.csvresults/qwen36_27b_v0/base/qwen36_27b_local_ft_v4_nvfp4_attention_output_bf16_modelopt_dgx_spark_rescored_v2/scores.csvreports/generated/hub/qwen36_local_ft_v4_nvfp4_attention_output_bf16_modelopt_public_publish_full_eval_20260607_retry_hf_transfer/supporting_evidence/full_eval_manifest_manifest.jsonreports/generated/serve_bench/qwen36_27b_local_ft_v4_nvfp4_attention_output_bf16_modelopt_tp2_core_20260606/summary.jsonreports/generated/quantization/qwen36_local_ft_v4_bf16_vs_nvfp4_attention_output_bf16_modelopt_20260606/quantization_card.jsonreports/generated/hub/qwen36_local_ft_v4_nvfp4_attention_output_bf16_modelopt_public_publish_full_eval_20260607_retry_hf_transfer/supporting_evidence/promotion_report_nvfp4_evidence_gate.jsonEvidence path rewrites applied for public release hygiene:
reports/generated/serving_evals/qwen36_27b_local_ft_v4_nvfp4_attention_output_bf16_modelopt_tp2_serving_eval_20260606 -> reports/generated/serving_evals/qwen36_27b_local_ft_v4_nvfp4_attention_output_bf16_modelopt_tp2_serving_eval_20260606/scores.csv (eval directories can contain private run manifests; scores.csv is the sanitized public evidence file)results/qwen36_27b_v0/base/qwen36_27b_local_ft_v4_nvfp4_attention_output_bf16_modelopt_dgx_spark_rescored_v2/manifest.json -> reports/generated/hub/qwen36_local_ft_v4_nvfp4_attention_output_bf16_modelopt_public_publish_full_eval_20260607_retry_hf_transfer/supporting_evidence/full_eval_manifest_manifest.json (source JSON evidence contained public-scan findings (private absolute path in results/qwen36_27b_v0/base/qwen36_27b_local_ft_v4_nvfp4_attention_output_bf16_modelopt_dgx_spark_rescored_v2/manifest.json); wrote a sanitized copy)results/qwen36_27b_v0/base/qwen36_27b_local_ft_v4_nvfp4_attention_output_bf16_modelopt_dgx_spark_rescored_v2 -> results/qwen36_27b_v0/base/qwen36_27b_local_ft_v4_nvfp4_attention_output_bf16_modelopt_dgx_spark_rescored_v2/scores.csv (eval directories can contain private run manifests; scores.csv is the sanitized public evidence file)reports/generated/quantization/qwen36_local_ft_v4_bf16_vs_nvfp4_attention_output_bf16_modelopt_20260606/nvfp4_evidence_gate.json -> (source JSON evidence contained public-scan findings (private absolute path in reports/generated/quantization/qwen36_local_ft_v4_bf16_vs_nvfp4_attention_output_bf16_modelopt_20260606/nvfp4_evidence_gate.json); wrote a sanitized copy)Quantization summary:
configs/model_families/qwen36_27b.yaml./forge hf plan-model qwen36_27b local_ft_v4_nvfp4_attention_output_bf16_modelopt --release-class public_quantized_modelThis is a no-ablation release for the Qwen 3.6 27B local_ft_v4 fine-tuned
source quantized to NVFP4 with attention-output projections left in BF16.
Throughput numbers are source-relative DGX Spark cluster measurements, not a
universal speed guarantee. Re-evaluate for your serving stack and prompts.
This is a released NVIDIA ModelOpt NVFP4 artifact, published on 2026-06-07 after the configured Model Forge release gates passed. The reports/, results/, and model_forge_quantization_summary.json files in this repository are the available release record.
The artifact requires an NVIDIA/CUDA, Transformers, and ModelOpt stack that supports its exported NVFP4 format and BF16 attention-output projections. Pin compatible versions and validate loading in the target serving environment. A portable first step is:
bash
hf download keithtyser/model-forge-qwen36-27b-ft-v4-nvfp4-dgx-spark --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 and the retained BF16 projections can affect accuracy, calibration, memory use, and safety behavior. Run task-specific, multimodal (if applicable), and safety evaluations before production use.
reports/generated/hub/qwen36_local_ft_v4_nvfp4_attention_output_bf16_modelopt_public_publish_full_eval_20260607_retry_hf_transfer/supporting_evidence/promotion_report_nvfp4_evidence_gate.json