ServingCard logoServingCard

devstral-small-24b

devstral-small-24b serving configurations from the ServingCard registry.

View on GitHub
Parameters24B
ArchitectureMistralForCausalLM
LicenseApache-2.0
Configs1 variant
Observations1
HuggingFace View on HuggingFace →

Benchmark Observations

zenprocessverified
Source

Throughput

53.6 tok/s

Latency

74ms TTFT

Quality

0.293

GPU

nvidia-gb10

vllm>=0.8.0Unknownbaseline

Fork This Config

Create your own optimized configuration based on these community-verified settings.

Open Configurator

Discussion

Debate benchmarks, share quirks, report what works and what doesn't on your hardware.