Skip to content

RTX PRO 6000 · Blackwell Server Edition

Most open weights fit on one 96 GB GPU.

Rent NVIDIA RTX PRO 6000 at $2.25 / GPU-hr, billed per second — 1–8 GPUs per node behind a private, OpenAI-compatible /v1 endpoint with one API key. Terminate anytime.

$2.25 / GPU-hr96 GB GDDR7 per GPUOpenAI-compatible /v1Terminate anytime
rtx pro 6000 — private /v1
# one GPU · 96 GB GDDR7 · billed per second
$ curl https://amber-crest-8841.skyforgecompute.com/v1/chat/completions \
    -H "Authorization: Bearer $SKYFORGE_API_KEY" \
    -d '{"model":"qwen3-6-35b-a3b","messages":[…]}'

{"choices":[{"message":{"content":"Served from 96 GB of GDDR7."}}]}

01Hardware

The spec sheet, not the pitch.

The numbers that decide whether your model fits on one GPU — verified hardware, nothing else.

SpecValueNotes
Memory96 GB GDDR7per GPU — most open-weights models fit without sharding
Memory bandwidth1,597 GB/sper GPU, feeding weights and KV cache
GPUs per node1–8pick a count at launch; one instance, one endpoint
Aggregate memoryup to 768 GBeight GPUs in a single node for larger serving

$2.25 / GPU-hr · billed per second from boot to terminate

Full pricing →

02Which models fit

Tier-S: one template, one GPU.

Five curated templates from the catalog run on a single RTX PRO 6000. Each link opens the console with the template preselected.

ModelArchitectureServedMax contextMin VRAM
GLM-4 9B9B densebf16128K24 GBLaunch →
Qwen3.6 27B27B densebf16256K80 GBLaunch →
Gemma 3 27Bgated27B densebf16128K80 GBLaunch →
DeepSeek-R1-Distill 32B32B densebf16128K80 GBLaunch →
Qwen3.6 35B-A3B35B MoE · 3B actbf16256K96 GBLaunch →

Every row fits a single RTX PRO 6000 (96 GB) — served with vLLM behind your private, OpenAI-compatible /v1.

Full catalog →

03Workloads

What teams run on it.

01

Inference serving

Serve open-weights chat and completion models behind a stable /v1 endpoint.

02

Fine-tuning & LoRA

Adapt open models to your data with LoRA or full fine-tunes on local NVMe.

03

Embeddings & RAG

Generate embeddings and back retrieval pipelines with the same endpoint.

04

Agents & tool use

Run agent harnesses with high request fan-out against your own models.

05

Batch & offline jobs

Spin up for a batch run, pay per second, and tear down when it finishes.

06

Notebooks & dev

Prototype in JupyterLab or VS Code Server with the full CUDA toolkit.

04Pricing

One rate. Per second. No gates.

On-demand is self-serve. Committed capacity is quoted by our enterprise team.

On-demand · self-serve

$2.25/ GPU-hr

Managed RTX PRO 6000 GPU-hours behind ready-to-run templates. 1–8 GPUs, billed per second, no commitment.

  • Per-second billing
  • OpenAI-compatible /v1 API
  • One API key across instances
  • Ready-to-run launch templates, or your own image
  • 1–8 GPUs, no commitment, no tier gates
  • Terminate anytime

05FAQ

Questions, answered.

Billing, compatibility, and scaling — the short version.

06Beyond on-demand

Steady workload? We'll quote it.

01

Committed-use pricing

Reserve capacity at committed-use rates when your workload is steady enough to plan around.

02

Private networking

Connect your fleet with private networking for production traffic.

03

Named support

Work with a named contact for onboarding, scaling, and incident response.