python3 -m vllm.entrypoints.openai.api_server \
  --host 0.0.0.0 --port 8000 \
  --model miike-ai/devstral-fp8 \
  --tokenizer mistralai/Devstral-Small-2505 \
  --tokenizer-mode mistral \
  --trust-remote-code
Downloads last month
167
Safetensors
Model size
23.6B params
Tensor type
BF16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for miike-ai/devstral-fp8

Quantized
(40)
this model

Collection including miike-ai/devstral-fp8