ornith-ai / text-generation updated 3 weeks ago

Ornith-1.5-397B-GGUF

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

Params
Context
Downloads 30d
1.4 M
Likes
37
Commercial use: allowed mit Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 27 days
1.4 M185 K
Aug 25Sep 3Sep 12Sep 20

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
mmproj-Ornith-1.5-397B-BF16.gguf GGUF 0.9 GB 1.5 GB ✅ Runs comfortably
Ornith-1.5-397B-Q4_K_M.gguf Q4_K_M 244.3 GB 269.2 GB ❌ Won’t fit
Ornith-1.5-397B-Q5_K_M.gguf Q5_K_M 286.3 GB 315.5 GB ❌ Won’t fit
Ornith-1.5-397B-Q6_K.gguf Q6_K 331.0 GB 364.6 GB ❌ Won’t fit
Ornith-1.5-397B-Q8_0.gguf Q8_0 428.5 GB 471.9 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
~ · ollama · Q4_K_M
$ ollama run ornith-1-5-397b-gguf

# pin the quantization explicitly
$ ollama run ornith-1-5-397b-gguf-q4_k_m
est. VRAM 269.2 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
mit
First seen on the Hub
2026-08-18
Training datasets
undisclosed
Added to our catalog
2026-08-25
Compare with any text-generation model