Qwen-72B vs Kimi-Linear-48B-A3B-Instruct
Specs, VRAM requirements and download trends — updated 7 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen-72B | Kimi-Linear-48B-A3B-Instruct |
|---|---|---|
| Parameters | 72.3 B | 49.1 B |
| Architecture | QWenLMHeadModel | KimiLinearForCausalLM |
| Context length | 32,768 | — |
| Licence | other | mit |
| Commercial use | Unknown | Allowed |
| Languages | 2 | — |
| Downloads 30d | 4,212,967 | 190,802 |
| Downloads all time | 7.5 M | 1.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-11-26 | 2025-10-30 |
Download trend
Daily snapshots, last 57 days (28 Jul – 22 Sep)
4.2 M176 K
Qwen-72B
Kimi-Linear-48B-A3B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Kimi-Linear-48B-A3B-Instruct · fp16
115.9 GB / 24 GB
Qwen-72B · fp16
170.4 GB / 24 GB