Qwen2.5-7B-Instruct vs Phi-tiny-MoE-instruct
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-7B-Instruct | Phi-tiny-MoE-instruct |
|---|---|---|
| Parameters | 7.6 B | 3.8 B |
| Architecture | Qwen2ForCausalLM | PhiMoEForCausalLM |
| Context length | 32,768 | 4,096 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 12,117,940 | 906,711 |
| Downloads all time | 165.8 M | 5.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-16 | 2025-06-23 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
12.2 M875 K
Qwen2.5-7B-Instruct
Phi-tiny-MoE-instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Phi-tiny-MoE-instruct · fp16
9.3 GB / 24 GB
Qwen2.5-7B-Instruct · fp16
18.4 GB / 24 GB