Qwen3-4B vs Inkling-Small-DSpark-Preview

Specs, VRAM requirements and download trends — updated 25 October 2026.

Qwen · A · Open weights
Params
4.0 B
Context
40,960
30d
11.4 M
apache-2.0 · commercial OK
RadixArk · B · Open weights
Params
1.4 B
Context
1,048,576
30d
151 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-4B Inkling-Small-DSpark-Preview
Parameters 4.0 B 1.4 B
Architecture Qwen3ForCausalLM DSparkDraftModel
Context length 40,960 1,048,576
Licence apache-2.0 —
Commercial use Allowed Unknown
Languages — —
Downloads 30d 11,364,244 151,192
Downloads all time 92.8 M 242 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-04-27 2026-07-30

Download trend

Daily snapshots, last 90 days (28 Jul – 25 Oct)

12.6 M151 K
Qwen3-4B Inkling-Small-DSpark-Preview

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Qwen3-4B · fp16 10.0 GB / 24 GB
✅ Runs comfortably
Inkling-Small-DSpark-Preview · fp16 @ 1024K ctx 29.3 GB / 24 GB
❌ Won’t fit

Adjacent comparisons