ornith-ai / text-generation updated 2 weeks 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

499 K

Likes

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

Download history

daily snapshots · 10 days

499 K221 K

Aug 31Sep 3Sep 6Sep 9

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": 498963,
  "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

gpt-oss-120b 5.4 M DeepSeek-V4-Flash-0731 4.4 M DeepSeek-V3.2 1.6 M GLM-5.2-FP8 1.3 M MiniMax-M2.7 1.3 M GLM-5.2-NVFP4 940 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB