Qwen3.6-35B-A3B-FP8 vs Unlimited-OCR-AWQ

Specs, VRAM requirements and download trends — updated 19 August 2026.

Qwen · A

Params

36.0 B

Context

—

30d

9.5 M

apache-2.0 · commercial OK

sahilchachra · B

Params

3.4 B

Context

32,768

30d

1.3 M

mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3.6-35B-A3B-FP8	Unlimited-OCR-AWQ
Parameters	36.0 B	3.4 B
Architecture	Qwen3_5MoeForConditionalGeneration	UnlimitedOCRForCausalLM
Context length	—	32,768
Licence	apache-2.0	mit
Commercial use	Allowed	Allowed
Languages	—	1
Downloads 30d	9,490,163	1,318,608
Downloads all time	42.8 M	2.4 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-04-15	2026-06-23

Daily snapshots, last 56 days (28 Jul – 21 Sep)

13.5 M817 K

Qwen3.6-35B-A3B-FP8 Unlimited-OCR-AWQ

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

Unlimited-OCR-AWQ · fp16 4.1 GB / 24 GB

✅ Runs comfortably

Qwen3.6-35B-A3B-FP8 · fp16 47.1 GB / 24 GB

❌ Won’t fit