ornith-ai / text-generation Open weights updated 2 months ago

Ornith-1.5-397B

Name: Ornith-1.5-397B
Author: ornith-ai

Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.

Params

403.4 B

Context

—

Downloads 30d

225 K

Likes

Commercial use: allowed mit Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 56 days

▲ 343 K in the last 30 days (60.3%)

636 K212 K

Aug 31Sep 18Oct 7Oct 25

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	806.8 GB	948.5 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/ornith-1-5-397b
{
  "hf_id": "ornith-ai/Ornith-1.5-397B",
  "params_b": 403.40,
  "context_length": null,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 225272,
  "vram_estimates": [
    { "quant": "bf16", "gb": 948.5 }
  ],
  "updated_at": "2026-08-31T01:00:18Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Qwen3_5MoeForConditionalGeneration
Parameters: 403.4 B
Tensor type: BF16
Licence: mit
First seen on the Hub: 2026-08-18
Training datasets: undisclosed
Added to our catalog: 2026-08-31

Compare with any text-generation model

Popular comparisons

DeepSeek-V3.2 5.6 M DeepSeek-V4-Flash-0731 4.3 M gpt-oss-120b 2.9 M GLM-5.3 2.0 M DeepSeek-R1 1.5 M NVIDIA-Nemotron-3-Super-120B-A12B-BF16 1.0 M