Downloads · 30 days
83
18% of all-time downloads
positron-ai/openai_gpt-oss-20b-ingest-best-gptq
openai_gpt-oss-20b-ingest-best-gptq is a text generation model from positron-ai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This repository contains a Positron AI quantized build of openai/gpt-oss-20b for tron inference on Positron FPGA-serving infrastructure.
Downloads · 30 days
83
18% of all-time downloads
All-time downloads
463
Public
Parameters
20.9B
13 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors13 GB · 100%
How the weights are stored.
I3219.7B · 94%
From the Hugging Face model README
This repository contains a Positron AI quantized build of openai/gpt-oss-20b for tron inference on Positron FPGA-serving infrastructure.
Use this artifact when you need a GPTQ 4-bit build of openai/gpt-oss-20b optimized for Positron's tron runtime. This build targets Positron's ingest-serving path, where runtime fidelity and FPGA deployability are prioritized over general-purpose GPU portability.
For general-purpose GPU inference, compare against the original model and other quantized formats before deployment.
| Field | Value |
|---|---|
| Base model | openai/gpt-oss-20b |
| Published artifact | openai_gpt-oss-20b-ingest-best-gptq |
| Quantization method | GPTQ |
| Quantization format | gptq |
| Source precision | bf16 |
| Target runtime | tron |
| Hardware target | FPGA |
| Release date | 2026-06-30 |
| 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 | false |
| Damp percent | 0.05 |
| Calibration dataset | Mixed-domain blend (multi-turn) |
| Calibration samples | 128 |
| Calibration sequence length | 1024 |
| MoE experts per token | 16 |
| Quantization toolchain | GPTQModel 5.8.0, transformers 4.57.6, 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 openai/gpt-oss-20b. The original model license and usage restrictions continue to apply.