Model library

Open models, with the GPU to run them.

Each model below names the GPU we recommend for it and opens the console with that GPU and model already picked. One-click presets start serving an OpenAI-compatible API on your own machine; the others you run yourself with the linked guide. SSH, the browser terminal and the rest of the machine stay yours either way.

One-click presets: the weights are already on the machine, pinned to a fixed revision.

QwenCoding · Text

Qwen3 Coder 30B

A coding model for agents and editors, with tool calls turned on.

One-click preset · vLLM · RTX 5090

QwenText

Qwen3.6 35B-A3B

A fast mixture-of-experts model for chat and agents, also on the pay-per-token API.

One-click preset · llama.cpp · DGX Spark

OpenAIText

GPT-OSS 120B

OpenAI's open-weight 120B model, quantized to fit one DGX Spark.

One-click preset · llama.cpp · DGX Spark

QwenText

Qwen3.8 Flash Next

A large Qwen3.8 mixture-of-experts model, quantized to fit one DGX Spark.

One-click preset · llama.cpp · DGX Spark

Z.aiText

GLM-5.3-Flash

A 320B mixture-of-experts model at a sub-2-bit quant, for the longest context on one Spark.

One-click preset · llama.cpp · DGX Spark

ComfyUIImage · Video

ComfyUI

The node editor for image and video workflows, in your browser. Bring your own checkpoints.

One-click preset · ComfyUI · DGX Spark

All models

Recommended GPU, rate and availability are read live. A one-click preset deploys the model; the others deploy a base image and link the setup guide.

Models with engine, size, recommended GPU and a deploy link
ModelEngineSizeRecommended GPUView or deploy
Qwen3 Coder 30BQwen · Coding · TextvLLM, llama.cppOne-click presetAWQ 4-bit · 5 configurationsRTX 5090$0.69 / hour · Check availability
Qwen3.6 35B-A3BQwen · Textllama.cpp, vLLMOne-click presetQ8_0 GGUF · 5 configurationsDGX Spark$0.79 / hour · Check availability
GPT-OSS 120BOpenAI · Textllama.cpp, vLLMOne-click presetUD-Q4_K_XL GGUF · 2 configurationsDGX Spark$0.79 / hour · Check availability
Qwen3.8 Flash NextQwen · Textllama.cpp, vLLMOne-click presetUD-Q3_K_XL GGUF · 4 configurationsDGX Spark$0.79 / hour · Check availability
GLM-5.3-FlashZ.ai · Textllama.cpp, vLLMOne-click presetUD-IQ1_S GGUF · 2 configurationsDGX Spark$0.79 / hour · Check availability
ComfyUIComfyUI · Image · VideoComfyUIOne-click presetBring your own checkpointsDGX Spark$0.79 / hour · Check availability
Gemma 4 26B-A4BGoogle · Text · MultimodalvLLM, llama.cppRun it yourselfNVFP4 · 4 configurationsDGX Spark$0.79 / hour · Check availability
Qwen3.8-27BQwen · Text · MultimodalvLLM, llama.cppRun it yourselfNVFP4, GGUF or BF16 · 5 configurationsDGX Spark$0.79 / hour · Check availability
Nemotron 3.5 Super VLNVIDIA · Multimodal · TextvLLM, llama.cppRun it yourselfNVFP4 · 2 configurationsDGX Spark$0.79 / hour · Check availability
Nemotron-3-Super-120BNVIDIA · TextvLLM, llama.cppRun it yourselfNVFP4 · 2 configurationsDGX Spark$0.79 / hour · Check availability
gpt-oss-20bOpenAI · Textllama.cpp, vLLMRun it yourselfMXFP4 · 3 configurationsDGX Spark$0.79 / hour · Check availability
Llama 3.3 70BMeta · TextvLLM, llama.cppRun it yourselfAWQ 4-bit · 2 configurationsDGX Spark$0.79 / hour · Check availability
Nemotron Super 49BNVIDIA · TextvLLM, llama.cppRun it yourselfNVFP4 · 3 configurationsDGX Spark$0.79 / hour · Check availability
DeepSeek-V4-FlashDeepSeek · TextvLLMRun it yourselfFP8 on two Sparks, 2-bit builds on one2 × DGX Spark$1.79 / hour · Check availability
Qwen3-235B-A22BQwen · Textllama.cpp, vLLMRun it yourselfQ4_K_XL GGUF2 × DGX Spark$1.79 / hour · Check availability

Model list checked 21 November 2026. Compare every GPU · Billing and stopped instances · Which models fit in 128 GB

Deploy your own

Not in the list? Every GPU you rent is a whole machine with root in your own container, so any open model that fits its memory runs on it.

Which models fit in 128 GB · Quantization explained · Choosing an inference engine