GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Billyjack3791
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Billyjack3791
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Parameter | Value |
|---|---|
| Source model | Qwen/Qwen3.6-27B |
| Quantization method | EXL3 |
| EXL3 version | v0.0.43 |
| Bits per weight | 4.00 |
| Codebook | mul1 |
| Calibration | 250 rows x 2048 columns |
Quantization was performed on dedicated workstation hardware with no errors or interruptions during the process.
| Component | Specification |
|---|---|
| CPU | Intel Core i7-9800X @ 3.80GHz (8C/16T) |
| Motherboard | ASUS WS X299 SAGE |
| RAM | 32GB DDR4-2666 |
| GPU(s) | 6x NVIDIA GeForce RTX 3070 8GB |
| Storage | MSI M480 PRO 1TB NVMe |
| OS | Ubuntu 24.04.4 LTS |
| Driver | NVIDIA 580.173.02 |
Orchestration: Quantization jobs were orchestrated from a dedicated control node (Intel i9-7920X, 62GB RAM, Quadro P5000 + RTX 3070 Ti + 2x RTX 3080) over a dedicated 10Gb interconnect to the compute node above. This separation ensured stable quantization with no I/O contention or control-plane interference during the GPU-heavy conversion process.
| File | Size |
|---|---|
| model-00001-of-00002.safetensors | 8.47 GB |
| model-00002-of-00002.safetensors | 8.39 GB |
| Total | 16.88 GB |
Compatible with TabbyAPI, EXL3V3 loader, and any runtime supporting EXL3 quantization.