Qwen3.6-35B-A3B-NVFP4 vs Ornith-1.5-9B-MLX-6bit

Specs, VRAM requirements and download trends — updated 21 September 2026.

nvidia · A
Params
18.7 B
Context
30d
8.0 M
apache-2.0 · commercial OK
ornith-ai · B
Params
9.0 B
Context
30d
226 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.6-35B-A3B-NVFP4 Ornith-1.5-9B-MLX-6bit
Parameters 18.7 B 9.0 B
Architecture Qwen3_5MoeForConditionalGeneration Qwen3_5ForConditionalGeneration
Context length
Licence apache-2.0
Commercial use Allowed Unknown
Languages 1
Downloads 30d 8,020,372 225,994
Downloads all time 34.6 M 228 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-05-27 2026-08-18

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

12.6 M199 K
Qwen3.6-35B-A3B-NVFP4 Ornith-1.5-9B-MLX-6bit

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Ornith-1.5-9B-MLX-6bit · fp16 9.8 GB / 24 GB
✅ Runs comfortably
Qwen3.6-35B-A3B-NVFP4 · fp16 29.1 GB / 24 GB
❌ Won’t fit

Adjacent comparisons