Qwen2.5-3B-Instruct vs Kimi-K3-DSpark
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-3B-Instruct | Kimi-K3-DSpark |
|---|---|---|
| Parameters | 3.1 B | 2.3 B |
| Architecture | Qwen2ForCausalLM | DSparkDraftModel |
| Context length | 32,768 | 1,048,576 |
| Licence | other | — |
| Commercial use | Unknown | Unknown |
| Languages | 1 | — |
| Downloads 30d | 5,952,246 | 798,444 |
| Downloads all time | 110.0 M | 798 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2026-07-27 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
6.0 M168 K
Qwen2.5-3B-Instruct
Kimi-K3-DSpark
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-3B-Instruct · fp16
7.8 GB / 24 GB
Kimi-K3-DSpark · fp16 @ 1024K ctx
48.6 GB / 24 GB