Qwen2.5-0.5B-Instruct vs mamba-130m-hf
Specs, VRAM requirements and download trends — updated 21 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-0.5B-Instruct | mamba-130m-hf |
|---|---|---|
| Parameters | 490 M | 130 M |
| Architecture | Qwen2ForCausalLM | MambaForCausalLM |
| Context length | 32,768 | — |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | 1 | — |
| Downloads 30d | 8,490,785 | 281,195 |
| Downloads all time | 69.2 M | 6.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-16 | 2024-03-06 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
8.5 M258 K
Qwen2.5-0.5B-Instruct
mamba-130m-hf
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
mamba-130m-hf · fp16
1.1 GB / 24 GB
Qwen2.5-0.5B-Instruct · fp16
1.7 GB / 24 GB