BR

briancaffey

@briancaffey

joined April 2026

club-host

offline 3D cluster
194 GB 4 GPUs7 services

a1

offline

a1 · 192.168.4.25

2 services
VRAM24 GB VRAM · declared
GeForce RTX 4090NVIDIA
magpie-tts TTS

Service · http://magpie-tts.inference-club.svc.cluster.local:9000/v1

magpie-tts-multilingual playground
Text
studio-voice ENHANCE

Service · http://studio-voice.inference-club.svc.cluster.local:8080/v1

Maxine Studio Voice (speech enhancement) playground
Audio

a2

offline

a2 · 192.168.5.96

1 service
VRAM24 GB VRAM · declared
GeForce RTX 4090NVIDIA
flux2-klein IMAGE

Service · http://flux2-klein.inference-club.svc.cluster.local:8000/v1

FLUX.2 Klein 4B playground
Text Image

a3

offline

a3 · 192.168.5.173

2 services
VRAM24 GB VRAM · declared
GeForce RTX 4090NVIDIA
dia TTS

Service · http://dia.inference-club.svc.cluster.local:8491

Dia 1.6B (voice cloning) playground
Text Audio voice-cloning dialogue
firecrawl SCRAPE

Service · http://firecrawl.inference-club.svc.cluster.local:3002/v1

Firecrawl (URL → markdown) playground
Text

spark

offline

spark-d2ce · 192.168.6.19

2 services
Memory122 GB unified · declared
GB10NVIDIA
acestep MUSIC

Service · http://acestep.inference-club.svc.cluster.local:8015

ACE-Step v1.5 Turbo playground
Text
nemotron-asr STT

Service · http://nemotron-asr.inference-club.svc.cluster.local:8105/v1

nvidia/nemotron-3.5-asr-streaming-0.6b playground
Audio

Compute provided

1,013 requests served · 13,184,755 tokens

Inference used

1,081 requests · 13,639,488 tokens (13,343,341 in / 296,147 out)

Models @briancaffey is serving

Run them free in the playground or from your own code via the OpenAI-compatible API.

curl https://api.inference.club/v1/chat/completions \
  -H "Authorization: Bearer $INFERENCE_CLUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "acestep-v15-turbo",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'