Qwen3.5-4B vs Qwen3.8-27B-NVFP4-RTX5090

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

Qwen · A
Params
4.7 B
Context
30d
6.8 M
apache-2.0 · commercial OK
gittensor-model-hub · B
Params
27.0 B
Context
30d
826 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.5-4B Qwen3.8-27B-NVFP4-RTX5090
Parameters 4.7 B 27.0 B
Architecture Qwen3_5ForConditionalGeneration Qwen3_5ForConditionalGeneration
Context length
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 6,819,426 826,347
Downloads all time 45.7 M 917 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-02-27 2026-08-14

Download trend

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

7.8 M826 K
Qwen3.5-4B Qwen3.8-27B-NVFP4-RTX5090

VRAM side by side

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

Qwen3.5-4B · fp16 11.5 GB / 24 GB
✅ Runs comfortably
Qwen3.8-27B-NVFP4-RTX5090 · fp16 24.3 GB / 24 GB
❌ Won’t fit

Adjacent comparisons