Qwen3.6-35B-A3B-FP8 vs Qwen3-VL-30B-A3B-Instruct

Specs, VRAM requirements and download trends — updated 3 August 2026.

Qwen · A
Params
36.0 B
Context
30d
8.9 M
apache-2.0 · commercial OK
Qwen · B
Params
31.1 B
Context
30d
860 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.6-35B-A3B-FP8 Qwen3-VL-30B-A3B-Instruct
Parameters 36.0 B 31.1 B
Architecture Qwen3_5MoeForConditionalGeneration Qwen3VLMoeForConditionalGeneration
Context length
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 8,946,336 859,932
Downloads all time 24.7 M 17.1 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-04-15 2025-09-30

Download trend

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

8.9 M860 K
Qwen3.6-35B-A3B-FP8 Qwen3-VL-30B-A3B-Instruct

VRAM side by side

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

Qwen3.6-35B-A3B-FP8 · fp16 47.1 GB / 24 GB
❌ Won’t fit
Qwen3-VL-30B-A3B-Instruct · fp16 73.5 GB / 24 GB
❌ Won’t fit

Adjacent comparisons