Qwen3-8B vs Phi-mini-MoE-instruct
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-8B | Phi-mini-MoE-instruct |
|---|---|---|
| Parameters | 8.2 B | 7.7 B |
| Architecture | Qwen3ForCausalLM | PhiMoEForCausalLM |
| Context length | 40,960 | 4,096 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 16,272,885 | 189,297 |
| Downloads all time | 103.2 M | 1.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2025-06-23 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
16.6 M178 K
Qwen3-8B
Phi-mini-MoE-instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Phi-mini-MoE-instruct · fp16
18.5 GB / 24 GB
Qwen3-8B · fp16
19.7 GB / 24 GB