Safetensors FL2VA / Online FP8
A quantized build of the model MiniMax-H3.
- Publisher
- MiniMaxAI
- Source platform
- HUGGINGFACE
- Quantization
- FL2VA / Online FP8
- Revision
- 42ed227ee7df40d41602854ae760620d6eb651fe
- Updated
- 2026-09-26
- Total size
- 134.16 GB
File list
Paths and sizes come from the release page; a missing size shows "not provided".
No file list provided.
Linked benchmarks
Only benchmarks tied to this exact release are listed.
| Hardware | Framework | Quant | Gen time | VRAM used | Samples | Evidence |
|---|---|---|---|---|---|---|
| NVIDIA DGX Spark | vLLM-Omni | Online dynamic FP8 | 80.6 s | 89.17 GB | 1 | L0 Self-reported |
Deployment guidance
This site doesn't guess whether or how this build runs on your machine. General local-deployment tutorials are linked below; if a link or data on this page is wrong, please tell us.