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/qwen3.5-4b-fp8
Q

Qwen3.5-4B (FP8-dynamic)

Alibaba / Qwen · Qwen3.5
Create a neuronet with this model →
LLMApache-2.0publicTrusted4B params
chatedgefp8quantizedsmall

Ready-made FP8-dynamic build of Qwen3.5-4B.

Ready-made FP8-dynamic build of Qwen3.5-4B.

At a glance

  • Task: LLM (InferenceV1)
  • Params: 4B
  • License: Apache-2.0 (commercial use OK)
  • Hardware: 9 GB+ VRAM
  • dtype: Fp8
Create a neuronet with this model →
Overview
Task
LLM · InferenceV1
Family
Qwen3.5
Tier
Trusted
Status
active
Runtime spec
dtype
Fp8
attention
FlashAttn2
compile
ReduceOverhead
seed
0
gpu_arch
Sm89
Runs on
Consumer, Datacenter
Hardware
Min VRAM
9 GB
Recommended
10 GB
Tensor parallel
≥1
TEE archs
Sm89, Sm90
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
RedHatAI/Qwen3.5-4B-FP8-dynamic ↗
Revision
397b7ba47a
Added
2026-08-03
Verified
2026-08-03