Qwen2.5-0.5B-Instruct vs mamba-130m-hf

Specs, VRAM requirements and download trends — updated 6 August 2026.

Qwen · A
Params
490 M
Context
32,768
30d
6.6 M
apache-2.0 · commercial OK
state-spaces · B
Params
130 M
Context
30d
846 K

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 6,560,475 845,516
Downloads all time 57.0 M 6.1 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 10 days (28 Jul – 6 Aug)

6.6 M816 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
✅ Runs comfortably
Qwen2.5-0.5B-Instruct · fp16 1.7 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons