briancaffey

@briancaffey

joined April 2026

1 agent4 GPUs4 services

club-host

offline

dgx-spark

dgx-spark · 192.168.6.19

DGX SparkNVIDIA

vLLMdgx-spark-vllm

http://192.168.6.19:8000/v1

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 playground

10K ctx Text Image Audio Reasoning

asr-box

192.168.5.173

RTX 4090NVIDIA

vLLMqwen3-asr

http://192.168.5.173:8000/v1

Qwen3-ASR-1.7B playground

64K ctx Audio

flux-box

192.168.5.96

RTX 4090NVIDIA

Otherflux-images

http://192.168.5.96:8000/v1

flux-2-klein playground

Text Image

riva-box

192.168.5.253

GPUNVIDIA

Othermagpie-tts

http://192.168.5.253:9000/v1

magpie-tts-multilingual playground

Text

Inference requests

@briancaffey hasn't made any inference requests yet.

Compute provided

87 requests served · 71,043 tokens

Inference used

87 requests · 71,043 tokens (45,012 in / 26,031 out)

Models @briancaffey is serving

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

Open in Playground Get an API key Docs

POST /chat/completions

curl https://api.inference.club/v1/chat/completions \
  -H "Authorization: Bearer $INFERENCE_CLUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2-klein",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.inference.club/v1",
    api_key="YOUR_INFERENCE_CLUB_API_KEY",
)

resp = client.chat.completions.create(
    model="flux-2-klein",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.inference.club/v1",
  apiKey: process.env.INFERENCE_CLUB_API_KEY,
})

const resp = await client.chat.completions.create({
  model: "flux-2-klein",
  messages: [{ role: "user", content: "Hello!" }],
})
console.log(resp.choices[0].message.content)