Qwen2.5-1.5B-Instruct vs MiniCPM5-2B-MLX
Specs, VRAM requirements and download trends — updated 24 October 2026.
Qwen · A · Open weights
Params
1.5 B
Context
32,768
30d
4.8 M
apache-2.0 · commercial OK
openbmb · B · Open weights
Params
2.5 B
Context
131,072
30d
548 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-1.5B-Instruct | MiniCPM5-2B-MLX |
|---|---|---|
| Parameters | 1.5 B | 2.5 B |
| Architecture | Qwen2ForCausalLM | LlamaForCausalLM |
| Context length | 32,768 | 131,072 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 2 |
| Downloads 30d | 4,779,599 | 547,635 |
| Downloads all time | 224.8 M | 696 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2026-09-05 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
14.2 M194 K
Qwen2.5-1.5B-Instruct
MiniCPM5-2B-MLX
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-1.5B-Instruct · fp16
4.1 GB / 24 GB
MiniCPM5-2B-MLX · fp16 @ 128K ctx
8.1 GB / 24 GB