Qwen2.5-0.5B-Instruct vs sarashina2.2-0.5b-instruct-v0.1
Specs, VRAM requirements and download trends — updated 21 September 2026.
sbintuitions · B
Params
790 M
Context
8,192
30d
248 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-0.5B-Instruct | sarashina2.2-0.5b-instruct-v0.1 |
|---|---|---|
| Parameters | 490 M | 790 M |
| Architecture | Qwen2ForCausalLM | LlamaForCausalLM |
| Context length | 32,768 | 8,192 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 8,490,785 | 247,967 |
| Downloads all time | 69.2 M | 317 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-16 | 2025-02-26 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
8.5 M220 K
Qwen2.5-0.5B-Instruct
sarashina2.2-0.5b-instruct-v0.1
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-0.5B-Instruct · fp16
1.7 GB / 24 GB
sarashina2.2-0.5b-instruct-v0.1 · fp16
2.4 GB / 24 GB