---
type: "Article"
title: "Ornith-1.5-122B EXL3 4 bpw with TensorFold on 1× DGX Spark"
description: "Ornith-1.5-122B EXL3 4 bpw with TensorFold on 1× DGX Spark: recipe by MiaAI-Lab with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/miaai-lab--ornith-1.5-122b-exl3-tensorfold-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:30:11.199Z"
status: "stable"
---

# Ornith-1.5-122B EXL3 4 bpw with TensorFold on 1× DGX Spark

Ornith-1.5-122B EXL3 4 bpw with TensorFold on 1× DGX Spark: 52.6 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [MiaAI-Lab](https://www.contextstudios.ai/local-ai/creators/miaai-lab.md)
- Engine: TensorFold tensorfold-native (Zig 0.17.0, pinned d1018b31 + recipe patches/ for EXL3 in the Qwen3.5-MoE engine), image tensorfold-ornith:zig-d1018b3, DFlash2 drafts
- Quantization: EXL3 EAQ v1 4 bpw (4.049 bpw trellis average per quant card), FP8 KV
- Model family: Ornith-1.5-122B
- Hardware: dgx-spark x1
- Context: 262144

## All numbers

- 52.6 tok/s (Everyday; Everyday, 1 request, prose prompt, with DFlash2 (per recipe)) — [source](https://github.com/MiaAI-Lab/Ornith-1.5-122B-TensorFold#performance)
- decode_tps: 52.6 (1 request) — [source](https://github.com/MiaAI-Lab/Ornith-1.5-122B-TensorFold#performance)
- decode_tps: 83.3 (1 request) — [source](https://github.com/MiaAI-Lab/Ornith-1.5-122B-TensorFold#performance)
- prefill_tps: 1955 (1 request) — [source](https://github.com/MiaAI-Lab/Ornith-1.5-122B-TensorFold#performance)
- ttft_ms: 164 (1 request) — [source](https://github.com/MiaAI-Lab/Ornith-1.5-122B-TensorFold#performance)

## Weights

- [Mia-AiLab/Ornith-1.5-122B-EXL3-EAQv1-4-bpw](https://huggingface.co/Mia-AiLab/Ornith-1.5-122B-EXL3-EAQv1-4-bpw) (main, mit)
- [ornith-ai/Ornith-1.5-122B](https://huggingface.co/ornith-ai/Ornith-1.5-122B) (base, mit)
- [incoai/Ornith-1.5-122B-DFlash2](https://huggingface.co/incoai/Ornith-1.5-122B-DFlash2) (draft, apache-2.0)

[https://github.com/MiaAI-Lab/Ornith-1.5-122B-TensorFold](https://github.com/MiaAI-Lab/Ornith-1.5-122B-TensorFold)

## Related

- [Local AI on your hardware.](https://www.contextstudios.ai/local-ai.md)