Ornith-1.0-9B-JANG_4M

OsaurusAI/Ornith-1.0-9B-JANG_4M

Ornith-1.0-9B-JANG_4M is a image-text-to-text model from OsaurusAI. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as mit.

Downloads · 30 days

4% of all-time downloads

All-time downloads

1.1K

Public

Parameters

9.4B

6.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors6.7 GB · 100%

Parameter types

How the weights are stored.

U329B · 95%

Try a prompt

Base models

Model card

From the Hugging Face model README

Ornith-1.0-9B · JANG_4M

Official OsaurusAI JANG_4M build of deepreinforce-ai/Ornith-1.0-9B (MIT) — a vision-language model on a Qwen3.5 hybrid backbone. Mixed-precision affine (JANG_4M); runs on Apple Silicon via Osaurus.

~6.3 GB (from ~18.8 GB bf16) bundle.
JANG_4M: 8-bit affine attention + 4-bit affine MLP (mixed precision, group-size 64); embeddings/head per-module; vision tower kept fp16.
Vision-language (image + text → text).

Architecture


Family	`qwen3_5` (dense, hybrid)
Text layers	32 — 24 Gated-DeltaNet (linear-attention) + 8 full-attention
MoE / dims	hidden 4096 · untied lm_head
Vision	ViT tower (`model.visual`) preserved fp16
Cache	hybrid (GDN state + KV for attention layers)
Parsers	reasoning `qwen3` · tools `qwen`

Running it

JANG bundles use the Qwen3.5 RMSNorm +1 scale_shift applied at runtime, so load them in Osaurus (or the vMLX runtime), which handles it automatically:

osaurus run OsaurusAI/Ornith-1.0-9B-JANG_4M

Note: a plain mlx_lm.generate will not be coherent on a JANG bundle — it omits the +1 norm shift. Use the Osaurus / vMLX runtime (or vmlx_engine.loaders.load_jang), which applies it.

Provenance

Quantization: Osaurus · JANG_4M (8-bit affine attention + 4-bit affine MLP, group-size 64; vision tower fp16) · [email protected]

Task: Image-Text-to-Text
Library: mlx
Type: qwen3_5
License: mit
Created: Jun 27, 2026
Updated: Jun 27, 2026