Kimi-K3-DSpark vs DeepSeek-R1-Distill-Qwen-1.5B
Specs, VRAM requirements and download trends — updated 21 September 2026.
deepseek-ai · B
Params
1.8 B
Context
131,072
30d
431 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Kimi-K3-DSpark | DeepSeek-R1-Distill-Qwen-1.5B |
|---|---|---|
| Parameters | 2.3 B | 1.8 B |
| Architecture | DSparkDraftModel | Qwen2ForCausalLM |
| Context length | 1,048,576 | 131,072 |
| Licence | — | mit |
| Commercial use | Unknown | Allowed |
| Languages | — | — |
| Downloads 30d | 3,658,082 | 430,987 |
| Downloads all time | 6.5 M | 21.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-27 | 2025-01-20 |
Download trend
Daily snapshots, last 51 days (2 Aug – 21 Sep)
3.7 M168 K
Kimi-K3-DSpark
DeepSeek-R1-Distill-Qwen-1.5B
A overtook B on 5 Aug
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-R1-Distill-Qwen-1.5B · fp16 @ 128K ctx
8.7 GB / 24 GB
Kimi-K3-DSpark · fp16 @ 1024K ctx
48.6 GB / 24 GB