Kimi-K3-DSpark vs Qwen2.5-VL-7B-Instruct-NVFP4
Specs, VRAM requirements and download trends — updated 30 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Kimi-K3-DSpark | Qwen2.5-VL-7B-Instruct-NVFP4 |
|---|---|---|
| Parameters | 2.3 B | 5.0 B |
| Architecture | DSparkDraftModel | Qwen2_5_VLForConditionalGeneration |
| Context length | 1,048,576 | 128,000 |
| Licence | — | other |
| Commercial use | Unknown | Unknown |
| Languages | — | — |
| Downloads 30d | 266,090 | 1,227,301 |
| Downloads all time | 11.1 M | 3.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-27 | 2025-09-10 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
6.6 M219 K
Kimi-K3-DSpark
Qwen2.5-VL-7B-Instruct-NVFP4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-VL-7B-Instruct-NVFP4 · fp16 @ 125K ctx
20.2 GB / 24 GB
Kimi-K3-DSpark · fp16 @ 1024K ctx
48.6 GB / 24 GB