Qwen3.6-35B-A3B-NVFP4 vs LLaDA-8B-Instruct

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

nvidia · A

Params

18.7 B

Context

—

30d

11.3 M

apache-2.0 · commercial OK

GSAI-ML · B

Params

8.0 B

Context

—

30d

429 K

mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3.6-35B-A3B-NVFP4	LLaDA-8B-Instruct
Parameters	18.7 B	8.0 B
Architecture	Qwen3_5MoeForConditionalGeneration	LLaDAModelLM
Context length	—	—
Licence	apache-2.0	mit
Commercial use	Allowed	Allowed
Languages	—	—
Downloads 30d	11,298,952	429,004
Downloads all time	19.7 M	5.6 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-05-27	2025-02-19

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

11.3 M384 K

Qwen3.6-35B-A3B-NVFP4 LLaDA-8B-Instruct

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

LLaDA-8B-Instruct · fp16 19.3 GB / 24 GB

✅ Runs comfortably

Qwen3.6-35B-A3B-NVFP4 · fp16 29.1 GB / 24 GB

❌ Won’t fit