Qwen2.5-32B-Instruct vs Ornith-1.5-35B-A3B-MLX

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

Qwen · A
Params
32.8 B
Context
32,768
30d
2.3 M
apache-2.0 · commercial OK
ornith-ai · B
Params
34.7 B
Context
30d
383 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen2.5-32B-Instruct Ornith-1.5-35B-A3B-MLX
Parameters 32.8 B 34.7 B
Architecture Qwen2ForCausalLM Qwen3_5MoeForConditionalGeneration
Context length 32,768
Licence apache-2.0
Commercial use Allowed Unknown
Languages 1 1
Downloads 30d 2,250,912 382,663
Downloads all time 30.9 M 390 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-09-17 2026-08-18

Download trend

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

2.3 M201 K
Qwen2.5-32B-Instruct Ornith-1.5-35B-A3B-MLX

VRAM side by side

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

Qwen2.5-32B-Instruct · fp16 77.5 GB / 24 GB
❌ Won’t fit
Ornith-1.5-35B-A3B-MLX · fp16 82.0 GB / 24 GB
❌ Won’t fit

Adjacent comparisons