OsaurusAI
NVIDIA-Nemotron-3-Ultra-550B-A55B-JANGTQ_1L
Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
License: otherBundle
- Format: JANGTQ
- Profile: JANGTQ_1L
- Family: nemotron_h
- Architecture: NemotronHForCausalLM
- Layers: 108
- TQ layout: prestacked_switch_mlp
- Runtime sidecar:
jangtq_runtime.safetensors - Chat template:
chat_template.jinja - Verified local size: 98G
Runtime Notes
This bundle is intended for text generation through JANGTQ-aware runtimes. It preserves the tokenizer, generation config, model index, quantization metadata, and TurboQuant runtime sidecar required by loaders.
Model provider
OsaurusAI
Model tree
Base
this model
Modalities
Input
Text
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information