Skip to content
AETRONConstructor
My neuronetsRegistrySpacesDocsFAQ
Sign in
AETRON

A constructor for AI services on AETRON’s decentralised network of GPU miners.

ProductCreate a neuronetModel catalogueDatasetsSpacesMy payouts
ResourcesDocumentationAPITimings & statusesFAQ
Networkaetron.ioPrivacy & verification
© 2026 AETRONTestnet
Models/qwen3.6-27b-nvfp4
Q

Qwen3.6-27B (NVFP4 (Blackwell))

Alibaba / Qwen · Qwen3.6
Create a neuronet with this model →
LLMApache-2.0publicTrusted27B params
chatflagshipinstructmultimodal-nativenvfp4quantized

Ready-made NVFP4 (Blackwell) build of Qwen3.6-27B. ModelOpt export - pending runtime support (transformers has no modelopt loader); catalog-only for now.

Ready-made NVFP4 (Blackwell) build of Qwen3.6-27B. ModelOpt export - pending runtime support (transformers has no modelopt loader); catalog-only for now.

At a glance

  • Task: LLM (InferenceV1)
  • Params: 27B
  • License: Apache-2.0 (commercial use OK)
  • Hardware: 25 GB+ VRAM
  • dtype: Nvfp4
Create a neuronet with this model →
Overview
Task
LLM · InferenceV1
Family
Qwen3.6
Tier
Trusted
Status
active
Runtime spec
dtype
Nvfp4
attention
FlashAttn2
compile
ReduceOverhead
seed
0
gpu_arch
Sm120
Runs on
Datacenter
Hardware
Min VRAM
25 GB
Recommended
28 GB
Tensor parallel
≥1
TEE archs
Sm120
Verification defaults
Tier
B
Trust
Level1
Security
Standard
Privacy
P0
Min pulse score
100
License
spdx
Apache-2.0 ↗
Commercial use
✓
Redistribution
✓
Source & provenance
Repo
nvidia/Qwen3.6-27B-NVFP4 ↗
Revision
0893e1606f
Added
2026-08-03
Verified
2026-08-03