Qwen2.5-Coder-32B-Instruct vs MiniMax-M2.5-NVFP4
Specs, VRAM requirements and download trends — updated 1 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-Coder-32B-Instruct | MiniMax-M2.5-NVFP4 |
|---|---|---|
| Parameters | 32.8 B | 116.4 B |
| Architecture | Qwen2ForCausalLM | MiniMaxM2ForCausalLM |
| Context length | 32,768 | 196,608 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | 1 | — |
| Downloads 30d | 1,317,270 | 221,989 |
| Downloads all time | 13.0 M | 1.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-11-06 | 2026-03-11 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
1.7 M222 K
Qwen2.5-Coder-32B-Instruct
MiniMax-M2.5-NVFP4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-32B-Instruct · fp16
77.5 GB / 24 GB
MiniMax-M2.5-NVFP4 · fp16 @ 192K ctx
573.2 GB / 24 GB