GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
positron-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
positron-ai
Model Tree
google/gemma-4-12B-it
Input Modalities
Output Modalities
Supported Functionality
Use this artifact when you need a GPTQ 4-bit build of google/gemma-4-12B-it built by Positron AI.
For general-purpose GPU inference, compare against the original model and other quantized formats before deployment.
| Field | Value |
|---|---|
| Base model | google/gemma-4-12B-it |
| Published artifact | positron-ai/google_gemma-4-12B-it-ingest-best-gptq-permuted |
| Quantization method | GPTQ |
| Quantization format | gptq |
| Source precision | n/a |
| Target runtime | n/a |
| Hardware target | n/a |
| Release date | 2026-09-02 |
| License | apache-2.0 |
| Field | Value |
|---|---|
| Weight precision | 4-bit |
| Activation precision | not quantized |
| Bits | 4 |
| Group size | 64 |
| Symmetric quantization | true |
| Activation ordering / desc_act | true |
| Damp percent | 0.05 |
| Calibration dataset | Mixed-domain calibration set |
| Calibration samples | 128 |
| Calibration sequence length | 4096 |
| MoE experts per token | n/a |
| Quantization toolchain | GPTQModel 7.1.0, transformers 5.11.0, torch 2.9.1, CUDA 12.8 |
This card intentionally reports no performance or quality metrics (no KL-divergence, accuracy, or perplexity figures). Validation results are tracked internally by Positron AI.
This artifact was produced by Positron AI from google/gemma-4-12B-it. The original model license and usage restrictions continue to apply.