gpt2 vs Qwen3.6-35B-A3B-DFlash

Specs, VRAM requirements and download trends — updated 6 August 2026.

openai-community · A
Params
140 M
Context
30d
13.7 M
mit · commercial OK
z-lab · B
Params
390 M
Context
262,144
30d
228 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification gpt2 Qwen3.6-35B-A3B-DFlash
Parameters 140 M 390 M
Architecture GPT2LMHeadModel DFlashDraftModel
Context length 262,144
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages 1
Downloads 30d 13,734,664 227,605
Downloads all time 901.9 M 543 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2022-03-02 2026-04-17

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

13.9 M222 K
gpt2 Qwen3.6-35B-A3B-DFlash

VRAM side by side

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

gpt2 · fp16 1.1 GB / 24 GB
✅ Runs comfortably
Qwen3.6-35B-A3B-DFlash · fp16 @ 256K ctx 3.2 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons