Capabilities · 18 artifacts
Models
Every quant, notebook, bench, and harness the Spark has shipped — each a card you can open to see its positioning, quant economics, and bounded drift, then drive straight into chat or a compare.
Offline patent-prosecution reasoning on Spark-class hardware
base deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
nemoOffline patent-prosecution reasoning on Spark-class hardware
base deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
nemoii-medical-8b-gguf
base Intelligent-Internet/II-Medical-8B
securityllm-gguf
base ZySec-AI/SecurityLLM
saul-7b-instruct-v1-gguf
base Equall/Saul-7B-Instruct-v1
finance-chat-gguf
base AdaptLLM/finance-chat
hermes-brain-bench-v0.1
base n/a
patent-strategist-bench-v0.1
base n/a
Build the finance-chat quant — and call the model — on a Spark or a free cloud GPU
base AdaptLLM/finance-chat
Build the Saul-7B quant — and call the legal model — on a Spark or a free cloud GPU
base Equall/Saul-7B-Instruct-v1
Build the SecurityLLM quant — and call the model — on a Spark or a free cloud GPU
base ZySec-AI/SecurityLLM
Build the II-Medical-8B quant — and call the reasoner — on a Spark or a free cloud GPU
base Intelligent-Internet/II-Medical-8B
Run the patent-strategist build — and use the model — on a Spark or a free cloud GPU
base deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
nemoAn operator cockpit you run on your own DGX Spark
base fieldkit[arena] · Astro + FastAPI sidecar
When does local stop being enough? Measure first, then route.
base Hermes Agent v0.14.0
The skills you write for Claude Code load into Hermes unchanged.
base agentskills.io SKILL.md (Hermes / Claude Code compatible)
Which local lane should drive your always-on Spark agent?
base Hermes Agent v0.14.0
One always-on brain, five specialists, zero LLM-classifier overhead.
base Hermes Agent v0.14.0