Qwen2.5-3B-Instruct vs Qwen3.8-27B-DSpark

Specs, VRAM requirements and download trends — updated 10 November 2026.

Qwen · A · Open weights
Params
3.1 B
Context
32,768
30d
2.6 M
RadixArk · B · Open weights
Params
1.9 B
Context
262,144
30d
190 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen2.5-3B-Instruct Qwen3.8-27B-DSpark
Parameters 3.1 B 1.9 B
Architecture Qwen2ForCausalLM DSparkDraftModel
Context length 32,768 262,144
Licence other other
Commercial use Unknown Unknown
Languages 1 —
Downloads 30d 2,587,484 190,418
Downloads all time 125.6 M 738 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-09-17 2026-08-14

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

7.6 M164 K
Qwen2.5-3B-Instruct Qwen3.8-27B-DSpark

VRAM side by side

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

Qwen2.5-3B-Instruct · fp16 7.8 GB / 24 GB
✅ Runs comfortably
Qwen3.8-27B-DSpark · fp16 @ 256K ctx 13.5 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons