# Ornith-1.0-397B Released – Has Anyone Tested It Yet or Found the Best Inference Settings?

**URL:** <https://forums.developer.nvidia.com/t/ornith-1-0-397b-released-has-anyone-tested-it-yet-or-found-the-best-inference-settings/374601>\
**Category:** DGX Spark / GB10\
**Tags:** ai-model-training\
**Created:** [June 26, 2026, 12:46am UTC](https://forums.developer.nvidia.com/t/ornith-1-0-397b-released-has-anyone-tested-it-yet-or-found-the-best-inference-settings/374601 "2026-06-26T00:46:54Z")\
**Posts on this page:** 1\
**Showing post:** 15

<div class="post-metadata">

**Author:** ![DannyTup](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/dannytup/32/450509_2.png) [@DannyTup](https://forums.developer.nvidia.com/u/DannyTup)\
**Post date:** [June 29, 2026, 6:58am UTC](https://forums.developer.nvidia.com/t/ornith-1-0-397b-released-has-anyone-tested-it-yet-or-found-the-best-inference-settings/374601/15 "2026-06-29T06:58:32Z")

</div>

> [@PILCOTHINK](#):
>
> I quantized the model to **INT4 (W4A16, group size 128)** using the pure RTN method with Intel AutoRound:

I don’t know if it was available at the time, but there’s an official FP8 version that’s \< 40GB, is it worth trying to go smaller?

> **[deepreinforce-ai/Ornith-1.0-35B-FP8 · Hugging Face](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-FP8)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

I’m currently running some benchmarks on it to compare to others on [GitHub - DanTup/spark-evals: Some benchmark results of small models and quants that fit on DGX Spark · GitHub](https://github.com/DanTup/spark-evals)

**Edit** : I misread, this thread is about the big version not 35B… I was reading two threads about this at the same time 😄

---

_[View the full topic](https://forums.developer.nvidia.com/t/ornith-1-0-397b-released-has-anyone-tested-it-yet-or-found-the-best-inference-settings/374601)._