Qwen2.5-32B-Instruct vs Ornith-1.5-35B-A3B-MLX-8bit
Specs, VRAM requirements and download trends — updated 22 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-32B-Instruct | Ornith-1.5-35B-A3B-MLX-8bit |
|---|---|---|
| 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 | 2,191,515 | 197,316 |
| Downloads all time | 31.0 M | 206 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 57 days (28 Jul – 22 Sep)
2.3 M197 K
Qwen2.5-32B-Instruct
Ornith-1.5-35B-A3B-MLX-8bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Ornith-1.5-35B-A3B-MLX-8bit · fp16
46.2 GB / 24 GB
Qwen2.5-32B-Instruct · fp16
77.5 GB / 24 GB