Qwen3.6-35B-A3B-NVFP4 vs EXAONE-3.5-7.8B-Instruct-AWQ

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

LGAI-EXAONE · B

Params

7.8 B

Context

32,768

30d

389 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3.6-35B-A3B-NVFP4	EXAONE-3.5-7.8B-Instruct-AWQ
Parameters	18.7 B	7.8 B
Architecture	Qwen3_5MoeForConditionalGeneration	ExaoneForCausalLM
Context length	—	32,768
Licence	apache-2.0	other
Commercial use	Allowed	Unknown
Languages	—	2
Downloads 30d	11,298,952	389,108
Downloads all time	19.7 M	637 K
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-05-27	2024-12-01

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

11.3 M295 K

Qwen3.6-35B-A3B-NVFP4 EXAONE-3.5-7.8B-Instruct-AWQ

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

EXAONE-3.5-7.8B-Instruct-AWQ · fp16 7.5 GB / 24 GB

✅ Runs comfortably

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

❌ Won’t fit