Phi-3.5-mini-instruct vs typhoon2.5-qwen3-4b
Specs, VRAM requirements and download trends — updated 13 August 2026.
microsoft · A · Open weights
Params
3.8 B
Context
131,072
30d
376 K
mit · commercial OK
typhoon-ai · B · Open weights
Params
4.0 B
Context
262,144
30d
138 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Phi-3.5-mini-instruct | typhoon2.5-qwen3-4b |
|---|---|---|
| Parameters | 3.8 B | 4.0 B |
| Architecture | Phi3ForCausalLM | Qwen3ForCausalLM |
| Context length | 131,072 | 262,144 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 375,768 | 138,295 |
| Downloads all time | 13.1 M | 1.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-08-16 | 2025-09-23 |
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
1.2 M138 K
Phi-3.5-mini-instruct
typhoon2.5-qwen3-4b
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Phi-3.5-mini-instruct · fp16 @ 128K ctx
18.1 GB / 24 GB
typhoon2.5-qwen3-4b · fp16 @ 256K ctx
28.6 GB / 24 GB