LLM
How to deploy MiniMax-H3 on a GPU cloud
A 33.1B language model for chat and instruction-following. Full specs, license and use cases.
MiniMax-H3 size and hardware requirements
33.1B
Total parameters
Dense (no MoE)
Architecture
BF16
Published precision
74.0 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 61.7 GB | 74.0 GB | A100 | 1 | $0.851/hr |
| FP8 (quantized) | 30.8 GB | 37.0 GB | RTX 6000 Ada | 1 | $0.524/hr |
| INT4 (quantized) | 15.4 GB | 18.5 GB | RTX 3090 | 1 | $0.147/hr |
How to run MiniMax-H3
Run MiniMax-H3 with SGLang
From MiniMaxAI/MiniMax-H3's own deployment docs.
# Original checkpoint, both task families (SGLang, vLLM):
hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" "Ref2VA/*" --local-dir MiniMax-H3
# Or a single task family:
hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" --local-dir MiniMax-H3Source: https://huggingface.co/MiniMaxAI/MiniMax-H3/raw/main/README.md
Run MiniMax-H3 with GGUF quantizations
Prebuilt GGUF weights published at unsloth/MiniMax-H3-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/MiniMax-H3-GGUFDeploy MiniMax-H3 on Aquanode
Aquanode has no one-click deploy template for MiniMax-H3; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× A100 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod