Qwen2-1.5B-Instruct vs Qwen2.5-1.5B-quantized.w8a8
Specs, VRAM requirements and download trends — updated 6 August 2026.
RedHatAI · B
Params
1.8 B
Context
32,768
30d
839 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2-1.5B-Instruct | Qwen2.5-1.5B-quantized.w8a8 |
|---|---|---|
| Parameters | 1.5 B | 1.8 B |
| Architecture | Qwen2ForCausalLM | Qwen2ForCausalLM |
| Context length | 32,768 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 3,182,072 | 839,449 |
| Downloads all time | 30.3 M | 7.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-06-03 | 2024-10-09 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
3.3 M831 K
Qwen2-1.5B-Instruct
Qwen2.5-1.5B-quantized.w8a8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-1.5B-quantized.w8a8 · fp16
3.2 GB / 24 GB
Qwen2-1.5B-Instruct · fp16
4.1 GB / 24 GB