Qwen3.6-35B-A3B-NVFP4 vs Phi-mini-MoE-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

microsoft · B

Params

7.7 B

Context

4,096

30d

189 K

mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3.6-35B-A3B-NVFP4	Phi-mini-MoE-instruct
Parameters	18.7 B	7.7 B
Architecture	Qwen3_5MoeForConditionalGeneration	PhiMoEForCausalLM
Context length	—	4,096
Licence	apache-2.0	mit
Commercial use	Allowed	Allowed
Languages	—	1
Downloads 30d	11,298,952	189,297
Downloads all time	19.7 M	1.2 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-05-27	2025-06-23

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

11.3 M178 K

Qwen3.6-35B-A3B-NVFP4 Phi-mini-MoE-instruct

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

Phi-mini-MoE-instruct · fp16 18.5 GB / 24 GB

✅ Runs comfortably

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

❌ Won’t fit