LLM
How to deploy Mixtral-8x7B-Instruct-v0.1 on a GPU cloud
A 46.7B (MoE) language model for chat and instruction-following. Full specs, license and use cases.
Mixtral-8x7B-Instruct-v0.1 size and hardware requirements
46.7B
Total parameters
Mixture-of-experts: 2 of 8 experts active per token (exact active-parameter count not stated on the model card)
Active parameters
BF16
Published precision
104.4 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 87.0 GB | 104.4 GB | RTX 3090 | 5 | $0.735/hr |
| FP8 (quantized) | 43.5 GB | 52.2 GB | RTX PRO 6000 | 1 | $1.64/hr |
| INT4 (quantized) | 21.7 GB | 26.1 GB | RTX A6000 | 1 | $0.330/hr |
How to run Mixtral-8x7B-Instruct-v0.1
Run Mixtral-8x7B-Instruct-v0.1 with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve mistralai/Mixtral-8x7B-Instruct-v0.1 --tensor-parallel-size 5Run Mixtral-8x7B-Instruct-v0.1 with GGUF quantizations
Prebuilt GGUF weights published at TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUFSource: https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF
Deploy Mixtral-8x7B-Instruct-v0.1 on Aquanode
Aquanode has no one-click deploy template for Mixtral-8x7B-Instruct-v0.1; 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 (5× RTX 3090 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