Documentation Navigation
Models & pricing / Models / BigBang-v1
BigBang-v1 Overview
Confirmed against endless-frontier documentation, August 2026
BigBang-v1 is a multimodal-general AI model created by endless-frontier, featuring 36.0B parameters and a context window of unknown.
SGLang is a high-performance serving framework for large language models and multimodal models, designed to deliver low-latency and high-throughput inference across various setups. It features a fast runtime, broad model support, and extensive hardware support.
Model Lineage & Specification
bigbang-v1 is endless-frontier's primary release in the current family.
bigbang-v1Comparable models
| Feature | BigBang-v1 | Muse-Glimmer-30B-GGUF | Minimax-H3-nvfp4-INT4-INT8-Convrot | Inkling |
|---|---|---|---|---|
| Description | SGLang is a high-performance serving framework for large language models and mul... | Muse-Glimmer-30B-GGUF is a undisclosed-parameter image text to text model develo... | Minimax-H3-nvfp4-INT4-INT8-Convrot is a undisclosed-parameter image text to vide... | Thinking Machines' flagship open-weights Mixture-of-Experts multimodal model, su... |
| API Identifier | bigbang-v1 | muse-glimmer-30b-gguf | minimax-h3-nvfp4-int4-int8-convrot | thinking-machines-inkling |
| Parameters | 36.0B | 29.6B | — | 975B (41B active) |
| Context Window | unknown | 131,072+ | unknown | 1000K tokens |
| License / Type | open weights | open weights | open weights | open weights |
BigBang-v1
SGLang is a high-performance serving framework for large language models and mul...
bigbang-v1Muse-Glimmer-30B-GGUF
Muse-Glimmer-30B-GGUF is a undisclosed-parameter image text to text model develo...
muse-glimmer-30b-ggufMinimax-H3-nvfp4-INT4-INT8-Convrot
Minimax-H3-nvfp4-INT4-INT8-Convrot is a undisclosed-parameter image text to vide...
minimax-h3-nvfp4-int4-int8-convrotInkling
Thinking Machines' flagship open-weights Mixture-of-Experts multimodal model, su...
thinking-machines-inklingSGLang is a high-performance serving framework for large language models and multimodal models, designed to deliver low-latency and high-throughput inference across various setups. It features a fast runtime, broad model support, and extensive hardware support.