Kimi-K3-DSpark vs Qwen2.5-Math-1.5B-Instruct
Specs, VRAM requirements and download trends — updated 19 October 2026.
Qwen · B · Open weights
Params
1.5 B
Context
4,096
30d
149 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Kimi-K3-DSpark | Qwen2.5-Math-1.5B-Instruct |
|---|---|---|
| Parameters | 2.3 B | 1.5 B |
| Architecture | DSparkDraftModel | Qwen2ForCausalLM |
| Context length | 1,048,576 | 4,096 |
| Licence | — | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | — | 1 |
| Downloads 30d | 266,090 | 149,168 |
| Downloads all time | 11.1 M | 3.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-27 | 2024-09-16 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
6.6 M137 K
Kimi-K3-DSpark
Qwen2.5-Math-1.5B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Math-1.5B-Instruct · fp16
4.1 GB / 24 GB
Kimi-K3-DSpark · fp16 @ 1024K ctx
48.6 GB / 24 GB