Qwen3.6-35B-A3B-NVFP4 vs Phi-3.5-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
41.9 B
Context
131,072
30d
161 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.6-35B-A3B-NVFP4 Phi-3.5-MoE-instruct
Parameters 18.7 B 41.9 B
Architecture Qwen3_5MoeForConditionalGeneration PhiMoEForCausalLM
Context length 131,072
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages 1
Downloads 30d 11,298,952 161,233
Downloads all time 19.7 M 2.1 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-05-27 2024-08-17

Download trend

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

11.3 M161 K
Qwen3.6-35B-A3B-NVFP4 Phi-3.5-MoE-instruct

VRAM side by side

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

Qwen3.6-35B-A3B-NVFP4 · fp16 29.1 GB / 24 GB
❌ Won’t fit
Phi-3.5-MoE-instruct · fp16 @ 128K ctx 193.1 GB / 24 GB
❌ Won’t fit

Adjacent comparisons